← Search

Lei Xie

95 accepted papers

2026

KALL-E: Autoregressive Speech Synthesis with Next-Distribution Prediction

AAAI 2026technical

We introduce KALL-E, a novel autoregressive (AR) language model for text-to-speech (TTS) synthesis that operates by predicting the next distribution of continuous speech frames. Unlike existing methods, KALL-E directly models the continuous speech distribution conditioned on text, eliminating the ne

Cited by 0SourcePDFScholar
2026

Learning Effective Sign Features without Text for Gloss-free Sign Language Translation

CVPR 2026

Self-supervised learning (SSL) has achieved remarkable success across both NLP and CV domains. However, sign language translation (SLT) models still heavily rely on gloss annotations in gloss-based SLT or text annotations in gloss-free SLT (GFSLT) during pretraining, aiming to ensure that the backbo

Cited by 0SourceScholar
2026

MEANVC: LIGHTWEIGHT AND STREAMING ZERO-SHOT VOICE CONVERSION VIA MEAN FLOWS

ICASSP 2026poster

Zero-shot voice conversion (VC) aims to transfer timbre from a source speaker to any unseen target speaker while preserving linguistic content. Growing application scenarios demand models with streaming inference capabilities. This has created a pressing need for models that are simultaneously fast,…

Cited by 0SourcePDFScholar
2026

SignPR: A Progressive Vector-Quantized Diffusion Framework for Sign Language Production

CVPR 2026

Sign language production aims to generate sign sequences from spoken language, where the generation of sign pose sequences from text is often treated as a significant task. However, due to the differences in grammatical rules and modalities between sign language pose sequences and spoken language te

Cited by 0SourceScholar
2026

THE ICASSP 2026 AUTOMATIC SONG AESTHETICS EVALUATION CHALLENGE

ICASSP 2026poster

This paper summarizes the ICASSP 2026 Automatic Song Aesthetics Evaluation (ASAE) Challenge, which focuses on predicting the subjective aesthetic scores of AI-generated songs. The challenge consists of two tracks: Track 1 targets the prediction of the overall musicality score, while Track 2 focuses…

Cited by 0SourcePDFScholar
2026

THE ICASSP 2026 HUMDIAL CHALLENGE: BENCHMARKING HUMAN-LIKE SPOKEN DIALOGUE SYSTEMS IN THE LLM ERA

ICASSP 2026poster

Driven by the rapid advancement of Large Language Models (LLMs), particularly Audio-LLMs and Omni-models, spoken dialogue systems have evolved significantly, progressively narrowing the gap between human-machine and human-human interactions. Achieving truly ``human-like'' communication necessitates…

Cited by 0SourcePDFScholar
2026

WENETSPEECH-CHUAN: A LARGE-SCALE SICHUANESE CORPUS WITH RICH ANNOTATION FOR DIALECTAL SPEECH PROCESSING

ICASSP 2026poster

The scarcity of large-scale, open-source data for dialects severely hinders progress in speech technology, a challenge particularly acute for the widely spoken Sichuanese dialects of Chinese. To address this critical gap, we introduce WenetSpeech-Chuan, a 10,000-hour, richly annotated corpus constru…

Cited by 0SourcePDFScholar
2026

WenetSpeech-Yue: A Large-Scale Cantonese Speech Corpus with Multi-dimensional Annotation

AAAI 2026technical

The development of speech understanding and generation has been significantly accelerated by the availability of large-scale, high-quality speech datasets. Among these, ASR and TTS are regarded as the most established and fundamental tasks. However, for Cantonese (Yue Chinese), spoken by approximate

Cited by 0SourcePDFScholar
2025

A Data-Driven Aggressive Autonomous Racing Framework Utilizing Local Trajectory Planning with Velocity Prediction

ICRA 2025

The development of autonomous driving has boosted the research on autonomous racing. However, existing local trajectory planning methods have difficulty planning trajectories with optimal velocity profiles at racetracks with sharp corners, thus weakening the performance of autonomous racing. To addr

Cited by 3SourcecodeScholar
2025

CAMEL: Cross-Attention Enhanced Mixture-of-Experts and Language Bias for Code-Switching Speech Recognition

ICASSP 2025accepted

Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the mixture-of-experts (MoE) architecture and an additional lan…

Cited by 0SourceScholar
2025

DiffAttack: Diffusion-based Timbre-reserved Adversarial Attack in Speaker Identification

ICASSP 2025accepted

Being a form of biometric identification, the security of the speaker identification (SID) system is of utmost importance. To better understand the robustness of SID systems, we aim to perform more realistic attacks in SID, which are challenging for humans and machines to detect. In this study, we p…

Cited by 0SourceScholar
2025

Drop the Beat! Freestyler for Accompaniment Conditioned Rapping Voice Generation

AAAI 2025technical

Rap, a prominent genre of vocal performance, remains underexplored in vocal generation. General vocal synthesis depends on precise note and duration inputs, requiring users to have related musical knowledge, which limits flexibility. In contrast, rap typically features simpler melodies, with a core…

2025

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

RSS 2025poster

Neural Networks (NNs) trained through supervised learning, struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving b…

Cited by 0PDFcodeScholar
2025

FSDP: Fast and Safe Data-Driven Overtaking Trajectory Planning for Head-to-Head Autonomous Racing Competitions

IROS 2025

Generating overtaking trajectories in autonomous racing is a challenging task, as the trajectory must satisfy the vehicle’s dynamics and ensure safety and real-time performance running on resource-constrained hardware. This work proposes the Fast and Safe Data-Driven Planner to address this challeng

Cited by 2SourcecodeScholar
2025

Freeze-Omni: A Smart and Low Latency Speech-to-speech Dialogue Model with Frozen LLM

ICML 2025poster

The GPT-4o's excellent duplex speech interaction ability has given users an impressive experience. Researchers have recently proposed several multimodal LLMs to achieve user-agent speech-to-speech conversations. In this paper, we propose a novel speech-text multimodal LLM architecture called Freeze-…

Cited by 32SourcePDFScholar
2025

GenSE: Generative Speech Enhancement via Language Models using Hierarchical Modeling

ICLR 2025poster

Semantic information refers to the meaning conveyed through words, phrases, and contextual relationships within a given linguistic structure. Humans can leverage semantic information, such as familiar linguistic patterns and contextual cues, to reconstruct incomplete or masked speech signals in nois…

Cited by 1SourcePDFScholar
2025

HDMoLE: Mixture of LoRA Experts with Hierarchical Routing and Dynamic Thresholds for Fine-Tuning LLM-based ASR Models

ICASSP 2025accepted

Recent advancements in integrating Large Language Models (LLM) with automatic speech recognition (ASR) have performed remarkably in general domains. While supervised fine-tuning (SFT) of all model parameters is often employed to adapt pre-trained LLM-based ASR models to specific domains, it imposes…

Cited by 0SourceScholar
2025

LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement

ACL 2025long

Recent advancements in language models (LMs) have demonstrated strong capabilities in semantic understanding and contextual modeling, which have flourished in generative speech enhancement (SE). However, many LM-based SE approaches primarily focus on semantic information, often neglecting the critic…

2025

Learning-Based On-Track System Identification for Scaled Autonomous Racing in Under a Minute

RA-L 2025

Accurate tire modeling is crucial for optimizing autonomous racing vehicles, as State-of-the-Art (SotA) modelbased techniques rely on precise knowledge of the vehicle's parameters, yet system identification in dynamic racing conditions is challenging due to varying track and tire conditions. Traditi

Cited by 13SourcecodeScholar
2025

MixSignGraph: A Sign Sequence is Worth Mixed Graphs of Nodes

NeurIPS 2025poster

Recent advances in sign language research have benefited from CNN-based backbones, which are primarily transferred from traditional computer vision tasks (\eg object detection, image recognition). However, these CNN-based backbones usually excel at extracting features like contours and texture, but…

Cited by 0SourcecodeScholar
2025

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

CVPR 2025poster

Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities, are limited by quadratic computational complexity…

2025

PVTNL: Prompting Vision Transformers with Natural Language for Generalizable Person Re-identification

EMNLP 2025

Domain generalization person re-identification (DG-ReID) aims to train models on source domains and generalize to unseen target domains.While patch-based Vision Transformers have achieved success in capturing fine-grained visual features, they often overlook global semantic structure and suffer from

Cited by 0SourcePDFScholar
2025

Predictive Spliner: Data-Driven Overtaking in Autonomous Racing Using Opponent Trajectory Prediction

RA-L 2025

Head-to-head racing against opponents is a challenging and emerging topic in the domain of autonomous racing. We propose Predictive Spliner, a data-driven overtaking planner designed to enhance competitive performance by anticipating opponent behavior. Using Gaussian Process (GP) regression, the met

Cited by 8SourcecodeScholar
2025

RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms

ICRA 2025

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. Reinforcement Learning (RL) methods

Cited by 4SourcecodeScholar
2025

Safe Reinforcement Learning with a Predictive Safety Filter for Motion Planning and Control: A Drifting Vehicle Example

IROS 2025

Autonomous drifting is a complex and crucial maneuver for safety-critical scenarios like slippery roads and emergency collision avoidance, requiring precise motion planning and control. Traditional motion planning methods often struggle with the high instability and unpredictability of drifting, par

Cited by 0SourceScholar
2025

StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching

AAAI 2025technical

Zero-shot voice conversion (VC) aims to transfer the timbre from the source speaker to an arbitrary unseen speaker while preserving the original linguistic content. Despite recent advancements in zero-shot VC using language model-based or diffusion-based approaches, several challenges remain: 1) cur…

2025

Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling

ACL 2025long

Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities. Despite recent progress in zero-shot VC, there remains considerable potential for im…

2025

ZSVC: Zero-shot Style Voice Conversion with Disentangled Latent Diffusion Models and Adversarial Training

ICASSP 2025accepted

Style voice conversion aims to transform the speaking style of source speech into a desired style while keeping the original speaker’s identity. However, previous style voice conversion approaches primarily focus on well-defined domains such as emotional aspects, limiting their practical application…

Cited by 0SourceScholar
2024

A Diffusion-Based Framework for Multi-Class Anomaly Detection

AAAI 2024technical

Reconstruction-based approaches have achieved remarkable outcomes in anomaly detection. The exceptional image reconstruction capabilities of recently popular diffusion models have sparked research efforts to utilize them for enhanced reconstruction of anomalous images. Nonetheless, these methods mig…

2024

Automatic Channel Selection and Spatial Feature Integration for Multi-Channel Speech Recognition Across Various Array Topologies

ICASSP 2024accepted

Automatic Speech Recognition (ASR) has shown remarkable progress, yet it still faces challenges in real-world distant scenarios across various array topologies each with multiple recording devices. The focal point of the CHiME-7 Distant ASR task is to devise a unified system capable of generalizing…

Cited by 0SourceScholar
2024

D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models

NeurIPS 2024poster

Large language models have shown an impressive societal impact owing to their excellent understanding and logical reasoning skills. However, such strong ability relies on a huge amount of computing resources, which makes it difficult to deploy LLMs on computing resource-constrained platforms. Curren…

Cited by 3SourcePDFScholar
2024

Dualvc 2: Dynamic Masked Convolution for Unified Streaming and Non-Streaming Voice Conversion

ICASSP 2024accepted

Voice conversion is becoming increasingly popular, and a growing number of application scenarios require models with streaming inference capabilities. The recently proposed DualVC attempts to achieve this objective through streaming model architecture design and intra-model knowledge distillation al…

Cited by 0SourceScholar
2024

MLCA-AVSR: Multi-Layer Cross Attention Fusion Based Audio-Visual Speech Recognition

ICASSP 2024accepted

While automatic speech recognition (ASR) systems degrade significantly in noisy environments, audio-visual speech recognition (AVSR) systems aim to complement the audio stream with noise-invariant visual cues and improve the system’s robustness. However, current studies mainly focus on fusing the we…

Cited by 0SourceScholar
2024

MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection

NeurIPS 2024poster

Recent advancements in anomaly detection have seen the efficacy of CNN- and transformer-based approaches. However, CNNs struggle with long-range dependencies, while transformers are burdened by quadratic computational complexity. Mamba-based models, with their superior long-range modeling and linear…

2024

Promptvc: Flexible Stylistic Voice Conversion in Latent Space Driven by Natural Language Prompts

ICASSP 2024accepted

Stylistic voice conversion aims to transform the style of source speech to a desired style according to real-world application demands. However, the current style voice conversion approach relies on pre-defined labels or reference speech to control the conversion process, which leads to limitations…

Cited by 0SourceScholar
2024

SELM: Speech Enhancement using Discrete Tokens and Language Models

ICASSP 2024accepted

Language models (LMs) have recently shown superior performances in various speech generation tasks, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech enhancement, harnessing semantic information is advantageous for…

Cited by 0SourceScholar
2024

SignGraph: A Sign Sequence is Worth Graphs of Nodes

CVPR 2024poster

Despite the recent success of sign language research the widely adopted CNN-based backbones are mainly migrated from other computer vision tasks in which the contours and texture of objects are crucial for identifying objects. They usually treat sign frames as grids and may fail to capture effecti…

2024

Spontts: Modeling and Transferring Spontaneous Style for TTS

ICASSP 2024accepted

Spontaneous speaking style exhibits notable differences from other speaking styles due to various spontaneous phenomena (e.g., filled pauses, prolongation) and substantial prosody variation (e.g., diverse pitch and duration variation, occasional non-verbal speech like a smile), posing challenges to…

Cited by 0SourceScholar
2024

StreamVoice: Streamable Context-Aware Language Modeling for Real-time Zero-Shot Voice Conversion

ACL 2024long

Recent language model (LM) advancements have showcased impressive zero-shot voice conversion (VC) performance. However, existing LM-based VC models usually apply offline conversion from source semantics to acoustic features, demanding the complete source speech and limiting their deployment to real-…

2023

A Hybrid Deep Neural Network for Nonlinear Causality Analysis in Complex Industrial Control System

ICASSP 2023accepted

It is important to efficiently and accurately locate the fault root cause to maintain the control performance, when the industrial control system fails. However, this task is very challenging because the industrial control system is large in scale and complex in connection. This paper proposes a nov…

Cited by 0SourceScholar
2023

Contrastive Learning for Sign Language Recognition and Translation

IJCAI 2023poster

There are two problems that widely exist in current end-to-end sign language processing architecture. One is the CTC spike phenomenon which weakens the visual representational ability in Continuous Sign Language Recognition (CSLR). The other one is the exposure bias problem which leads to the accumu…

Cited by 12SourcePDFScholar
2023

DSPGAN: A Gan-Based Universal Vocoder for High-Fidelity TTS by Time-Frequency Domain Supervision from DSP

ICASSP 2023accepted

Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogram with fast inference speed and lightweight networks. Whereas, it is still challenging to train a universal neural vocod…

Cited by 0SourceScholar
2023

Delivering Speaking Style in Low-Resource Voice Conversion with Multi-Factor Constraints

ICASSP 2023accepted

Conveying the linguistic content and maintaining the source speech’s speaking style, such as intonation and emotion, is essential in voice conversion (VC). However, in a low-resource situation, where only limited utterances from the target speaker are accessible, existing VC methods are hard to meet…

Cited by 0SourceScholar
2023

Distance-Based Weight Transfer for Fine-Tuning From Near-Field to Far-Field Speaker Verification

ICASSP 2023accepted

The scarcity of labeled far-field speech is a constraint for training superior far-field speaker verification systems. In general, fine-tuning the model pre-trained on large-scale near- field speech through a small amount of far-field speech substantially outperforms training from scratch. However,…

Cited by 0SourceScholar
2023

Distinguishable Speaker Anonymization Based on Formant and Fundamental Frequency Scaling

ICASSP 2023accepted

Speech data on the Internet are proliferating exponentially because of the emergence of social media, and the sharing of such personal data raises obvious security and privacy concerns. One solution to mitigate these concerns involves concealing speaker identities before sharing speech data, also re…

Cited by 0SourceScholar
2023

Expressive-VC: Highly Expressive Voice Conversion with Attention Fusion of Bottleneck and Perturbation Features

ICASSP 2023accepted

Voice conversion for highly expressive speech is challenging. Current approaches struggle with the balance between speaker similarity, intelligibility, and expressiveness. To address this problem, we propose Expressive-VC, a novel end-to-end voice conversion framework that leverages advantages from…

Cited by 0SourceScholar
2023

Multi-Speaker Expressive Speech Synthesis via Multiple Factors Decoupling

ICASSP 2023accepted

This paper aims to synthesize the target speaker’s speech with desired speaking style and emotion by transferring the style and emotion from reference speech recorded by other speakers. We address this challenging problem with a two-stage framework composed of a text-to-style-and-emotion (Text2SE) m…

Cited by 0SourceScholar
2023

Preserving Background Sound in Noise-Robust Voice Conversion Via Multi-Task Learning

ICASSP 2023accepted

Background sound is an informative form of art that is helpful in providing a more immersive experience in real-application voice conversion (VC) scenarios. However, prior research about VC, mainly focusing on clean voices, pay rare attention to VC with background sound. The critical problem for pre…

Cited by 0SourceScholar
2023

Robo-Centric ESDF: A Fast and Accurate Whole-Body Collision Evaluation Tool for Any-Shape Robotic Planning

IROS 2023poster

For letting mobile robots travel flexibly through complicated environments, increasing attention has been paid to the whole-body collision evaluation. Most existing works either opt for the conservative corridor-based methods that impose strict requirements on the corridor generation, or ESDF-based…

Cited by 15SourceScholar
2023

The NPU-Elevoc Personalized Speech Enhancement System for Icassp2023 DNS Challenge

ICASSP 2023accepted

This paper describes our NPU-Elevoc personalized speech enhancement system (NAPSE) for the 5th Deep Noise Suppression Challenge[1] at ICASSP 2023. Based on the superior two-stage model TEA-PSE 2.0 [2], our system particularly explores better strategy for speaker embedding fusion, optimizes the model…

Cited by 0SourceScholar
2023

Two-Stage Neural Network for ICASSP 2023 Speech Signal Improvement Challenge

ICASSP 2023accepted

In ICASSP 2023 speech signal improvement challenge, we developed a dual-stage neural model which improves speech signal quality induced by different distortions in a stage-wise divide-and-conquer fashion. Specifically, in the first stage, the speech improvement network focuses on recovering the miss…

Cited by 0SourceScholar
2023

Two-Step Band-Split Neural Network Approach For Full-Band Residual Echo Suppression

ICASSP 2023accepted

This paper describes a Two-step Band-split Neural Network (TBNN) approach for full-band acoustic echo cancellation. Specifically, after linear filtering, we split the full-band signal into wideband (16KHz) and high-band (16-48KHz) for residual echo removal with lower modeling difficulty. The wide-ba…

Cited by 0SourceScholar
2023

UniSyn: An End-to-End Unified Model for Text-to-Speech and Singing Voice Synthesis

AAAI 2023technical

Text-to-speech (TTS) and singing voice synthesis (SVS) aim at generating high-quality speaking and singing voice according to textual input and music scores, respectively. Unifying TTS and SVS into a single system is crucial to the applications requiring both of them. Existing methods usually suffer…

Cited by 10SourcePDFScholar
2023

VE-KWS: Visual Modality Enhanced End-to-End Keyword Spotting

ICASSP 2023accepted

The performance of the keyword spotting (KWS) system based on audio modality, commonly measured in false alarms and false rejects, degrades significantly under the far field and noisy conditions. Therefore, audio-visual keyword spotting, which leverages complementary relationships over multiple moda…

Cited by 0SourceScholar
2023

Wekws: A Production First Small-Footprint End-to-End Keyword Spotting Toolkit

ICASSP 2023accepted

Keyword spotting (KWS) enables speech-based user interaction and gradually becomes an indispensable component of smart devices. Recently, end-to-end (E2E) methods have be-come the most popular approach for on-device KWS tasks. However, there is still a gap between the research and deployment of E2E…

Cited by 0SourceScholar
2022

A Transformer-Based Object Detector with Coarse-Fine Crossing Representations

NeurIPS 2022accept

Transformer-based object detectors have shown competitive performance recently. Compared with convolutional neural networks limited by the relatively small receptive fields, the advantage of transformer for visual tasks is the capacity to perceive long-range dependencies among all image patches, wh…

Cited by 7SourcePDFScholar
2022

An Efficient Framework for Detection and Recognition of Numerical Traffic Signs

ICASSP 2022accepted

Due to the variety of categories and uneven distribution of available samples, automatic traffic sign detection and recognition is still a challenging task. For those categories with less training data, existing deep learning methods cannot achieve desirable performance, and the overall detection ef…

Cited by 0SourceScholar
2022

Combined Fast Control of Drifting State and Trajectory Tracking for Autonomous Vehicles Based on MPC Controller

ICRA 2022poster

Slipping may cause a vehicle out of control with serious accident potential. However, a kind of car slipping named “drifting” can be seen in professional contests. So, it is reasonable to apply drift maneuvers in autonomous driving. This article proposes a controller for the particular driving skill…

Cited by 16SourceScholar
2022

Conversational Speech Recognition by Learning Conversation-Level Characteristics

ICASSP 2022accepted

Conversational automatic speech recognition (ASR) is a task to recognize conversational speech including multiple speakers. Unlike sentence-level ASR, conversational ASR can naturally take advantages from specific characteristics of conversation, such as role preference and topical coherence. This p…

Cited by 0SourceScholar
2022

M2Met: The Icassp 2022 Multi-Channel Multi-Party Meeting Transcription Challenge

ICASSP 2022accepted

Recent development of speech signal processing, such as speech recognition, speaker diarization, etc., has inspired numerous applications of speech technologies. The meeting scenario is one of the most valuable and, at the same time, most challenging scenarios for the deployment of speech technologi…

Cited by 0SourceScholar
2022

Multi-Task Deep Residual Echo Suppression with Echo-Aware Loss

ICASSP 2022accepted

This paper introduces the NWPU Team’s entry to the ICASSP 2022 AEC Challenge. We take a hybrid approach that cascades a linear AEC with a neural post-filter. The former is used to deal with the linear echo components while the latter suppresses the residual non-linear echo components. We use gated c…

Cited by 0SourceScholar
2022

One-Shot Voice Conversion For Style Transfer Based On Speaker Adaptation

ICASSP 2022accepted

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the recognition-synthesis framework and propose a one-shot voice conversion…

Cited by 0SourceScholar
2022

S-DCCRN: Super Wide Band DCCRN with Learnable Complex Feature for Speech Enhancement

ICASSP 2022accepted

In speech enhancement, complex neural network has shown promising performance due to their effectiveness in processing complex-valued spectrum. Most of the recent speech enhancement approaches mainly focus on wide-band signal with a sampling rate of 16K Hz. However, research on super wide band (e.g.…

Cited by 0SourceScholar
2022

Summary on the ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Grand Challenge

ICASSP 2022accepted

The ICASSP 2022 Multi-channel Multi-party Meeting Transcription Grand Challenge (M2MeT) focuses on one of the most valuable and the most challenging scenarios of speech technologies. The M2MeT challenge has particularly set up two tracks, speaker diarization (track 1) and multi-speaker automatic spe…

Cited by 0SourceScholar
2022

TEA-PSE: Tencent-Ethereal-Audio-Lab Personalized Speech Enhancement System for ICASSP 2022 DNS Challenge

ICASSP 2022accepted

This paper describes Tencent Ethereal Audio Lab – Northwestern Polytechnical University personalized speech enhancement (TEA-PSE) system submitted to track 2 of the ICASSP 2022 Deep Noise Suppression (DNS) challenge. Our system specifically combines the dual-stage network which is a superior real-ti…

Cited by 56SourceScholar
2022

Uformer: A Unet Based Dilated Complex & Real Dual-Path Conformer Network for Simultaneous Speech Enhancement and Dereverberation

ICASSP 2022accepted

Complex spectrum and magnitude are considered as two major features of speech enhancement and dereverberation. Traditional approaches always treat these two features separately, ignoring their underlying relationship. In this paper, we propose Uformer, a Unet based dilated complex & real dual-path c…

Cited by 0SourceScholar
2022

VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis

ICASSP 2022accepted

In this paper, we propose VISinger, a complete end-to-end high-quality singing voice synthesis (SVS) system that directly generates singing audio from lyrics and musical score. Our approach is inspired by VITS [1], an end-to-end speech generation model which adopts VAE-based posterior encoder augmen…

Cited by 0SourceScholar
2022

WENETSPEECH: A 10000+ Hours Multi-Domain Mandarin Corpus for Speech Recognition

ICASSP 2022accepted

In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of…

Cited by 0SourceScholar
2021

An Asynchronous WFST-Based Decoder for Automatic Speech Recognition

ICASSP 2021accepted

We introduce asynchronous dynamic decoder, which adopts an efficient A* algorithm to incorporate big language models in the one-pass decoding for large vocabulary continuous speech recognition. Unlike standard one-pass decoding with on-the-fly composition decoder which might induce a significant com…

Cited by 0SourceScholar
2021

The Accented English Speech Recognition Challenge 2020: Open Datasets, Tracks, Baselines, Results and Methods

ICASSP 2021accepted

The variety of accents has posed a big challenge to speech recognition. The Accented English Speech Recognition Challenge (AESRC2020) is designed for providing a common testbed and promoting accent-related research. Two tracks are set in the challenge – English accent recognition (track 1) and accen…

Cited by 0SourceScholar
2021

The Multi-Speaker Multi-Style Voice Cloning Challenge 2021

ICASSP 2021accepted

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited d…

Cited by 0SourceScholar
2020

Mining Effective Negative Training Samples for Keyword Spotting

ICASSP 2020accepted

Max-pooling neural network architectures have been proven to be useful for keyword spotting (KWS), but standard training methods suffer from a class-imbalance problem when using all frames from negative utterances. To address the problem, we propose an innovative algorithm, Regional Hard-Example (RH…

Cited by 23SourceScholar
2020

Sequence to Multi-Sequence Learning via Conditional Chain Mapping for Mixture Signals

NeurIPS 2020poster

Neural sequence-to-sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on one-to-many sequence transduction problems, such as extracting multiple sequential sources from a mixture sequence.…

2020

Time-Domain Neural Network Approach for Speech Bandwidth Extension

ICASSP 2020accepted

In this paper, we study the time-domain neural network approach for speech bandwidth extension. We propose a network architecture, named multi-scale fusion neural network (MfNet), that gradually restores the low-frequency signal and predicts the high-frequency signal through the exchange of informat…

Cited by 0SourceScholar
2019

Adversarial Examples for Improving End-to-end Attention-based Small-footprint Keyword Spotting

ICASSP 2019accepted

In this paper, we explore the use of adversarial examples for improving a neural network based keyword spotting (KWS) system. Specially, in our system, an effective and small-footprint attention-based neural network model is used. Adversarial example is defined as a misclassified example by a model,…

Cited by 0SourceScholar
2019

An Attention-based Neural Network Approach for Single Channel Speech Enhancement

ICASSP 2019accepted

This paper proposes an attention-based neural network approach for single channel speech enhancement. Our work is inspired by the recent success of attention models in sequence-to-sequence learning. It is intuitive to use attention mechanism in speech enhancement as humans are able to focus on the i…

Cited by 56SourceScholar
2019

Component Fusion: Learning Replaceable Language Model Component for End-to-end Speech Recognition System

ICASSP 2019accepted

Recently, attention-based end-to-end automatic speech recognition system (ASR) has shown promising results. One of the limitations of an attention-based ASR system is that its language model (LM) component has to be implicitly learned from transcribed speech data which prevents one from uti-lizing p…

Cited by 0SourceScholar
2019

Domain Adversarial Training for Improving Keyword Spotting Performance of ESL Speech

ICASSP 2019accepted

A second language (L2) learner usually cannot speak L2 well in both pronunciations and forming-of-words. Hence his/her L2 speech cannot be well recognized by a recognizer trained with native data. Domain adversarial training (DAT), capable of reducing the acoustic mismatch between training and testi…

Cited by 0SourceScholar
2019

Enhancing Hybrid Self-attention Structure with Relative-position-aware Bias for Speech Synthesis

ICASSP 2019accepted

Compared with the conventional "front-end"-"back-end"- "vocoder" structure, based on the attention mechanism, end-to-end speech synthesis systems directly train and synthesize from text sequence to the acoustic feature sequence as a whole. Recently, a more calculation efficient end-to-end architectu…

Cited by 0SourceScholar
2019

Investigating End-to-end Speech Recognition for Mandarin-english Code-switching

ICASSP 2019accepted

Code-switching is a common phenomenon in many multilingual communities and presents a challenge to automatic speech recognition (ASR). In this paper, three approaches are investigated to improve end-to-end speech recognition on Mandarin-English code-switching task. First, multi-task learning (MTL) i…

Cited by 0SourceScholar
2019

Robust Audio-visual Speech Recognition Using Bimodal Dfsmn with Multi-condition Training and Dropout Regularization

ICASSP 2019accepted

Audio-visual speech recognition (AVSR) is thought to be one of the potential solutions for robust speech recognition, especially in noisy environments. Compared to audio only speech recognition, the major issues of AVSR include the lack of publicly available audio-visual corpora and the need of robu…

Cited by 0SourceScholar
2018

Domain Adversarial Training for Accented Speech Recognition

ICASSP 2018accepted

In this paper, we propose a domain adversarial training (DAT) algorithm to alleviate the accented speech recognition problem. In order to reduce the mismatch between labeled source domain data (“standard” accent) and unlabeled target domain data (with heavy accents), we augment the learning objectiv…

Cited by 148SourceScholar
2018

Unsupervised Domain Adaptation via Domain Adversarial Training for Speaker Recognition

ICASSP 2018accepted

The i-vector approach to speaker recognition has achieved good performance when the domain of the evaluation dataset is similar to that of the training dataset. However, in realworld applications, there is always a mismatch between the training and evaluation datasets, that leads to performance degr…

Cited by 0SourceScholar
2017

Pairwise learning using multi-lingual bottleneck features for low-resource query-by-example spoken term detection

ICASSP 2017accepted

We propose to use a feature representation obtained by pairwise learning in a low-resource language for query-by-example spoken term detection (QbE-STD). We assume that word pairs identified by humans are available in the low-resource target language. The word pairs are parameterized by a multi-ling…

Cited by 0SourceScholar
2016

Approximate search of audio queries by using DTW with phone time boundary and data augmentation

ICASSP 2016accepted

Dynamic Time Warping (DTW) is widely used in language independent query-by-example (QbE) spoken term detection (STD) tasks due to its high performance. However, there are two limitations of DTW based template matching, 1) it is not straightforward to perform approximate match of audio queries; 2) DT…

Cited by 0SourceScholar
2016

Exemplar-based sparse representation of timbre and prosody for voice conversion

ICASSP 2016accepted

Voice conversion (VC) aims to make one speaker (source) to sound like spoken by another speaker (target) without changing the language content. Most of the state-of-the-art voice conversion systems focus only on timbre conversion. However, the speaker identity is characterized by the source-related…

Cited by 0SourceScholar
2015

Language independent query-by-example spoken term detection using N-best phone sequences and partial matching

ICASSP 2015accepted

In this paper, we propose a partial sequence matching based symbolic search (SS) method for the task of language independent query-by-example spoken term detection. One main drawback of conventional SS approach is the high miss rate for long queries. This is due to high variations in symbol represen…

Cited by 0SourceScholar