95 accepted papers
Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models
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
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
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,…
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
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…
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…
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…
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
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
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…
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…
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…
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…
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
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-…
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…
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…
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…
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
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…
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…
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
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
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
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
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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-…
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…
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…
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…
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…
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,…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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…
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.…
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…
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…
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…
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…
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…
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…
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…
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…
Modern wake word detection systems usually rely on neural networks for acoustic modeling. Transformers has recently shown superior performance over LSTM and convolutional networks in various sequence modeling tasks with their better temporal modeling power. However it is not clear whether this advan…
WaveNet has shown its great potential as a direct conversion model in voice conversion. However, due to the model complexity, WaveNet always requires a large amount of training data, which has limited its applications in voice conversion, where training data is scarce. In this paper, we propose a Wa…
Graph Neural Networks (GNNs) are powerful for the representation learning of graph-structured data. Most of the GNNs use a message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information from its neighbors. To achieve a better expressive capability of node…
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…
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.…
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…
Despite significant advancements of deep learning on separating speech sources mixed in a single channel, same gender speaker mix, i.e., male-male or female-female, is still more difficult to separate than the case of opposite gender mix. In this study, we propose a pitch-aware speech separation app…
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,…
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…
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…
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…
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…
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…
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…
Recently, there has been a growing interest in end-to-end speech recognition that directly transcribes speech to text without any predefined alignments. In this paper, we explore the use of attention-based encoder-decoder model for Mandarin speech recognition on a voice search task. Previous attempt…
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…
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…
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…
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…
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…
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…
Long short-term memory (LSTM) is a specific recurrent neural network (RNN) architecture that is designed to model temporal sequences and their long-range dependencies more accurately than conventional RNNs. In this paper, we propose to use deep bidirectional LSTM (BLSTM) for audio/visual modeling in…