24 accepted papers
Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing E2E approaches primarily fall into two categories: (1) Methods that genera…
Movie dubbing is the task of synthesizing speech from scripts conditioned on video scenes, requiring accurate lip sync, faithful timbre transfer, and proper modeling of character identity and emotion. However, existing methods face two major limitations: (1) high-quality multimodal dubbing datasets
Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligence. Despite substantial methodological progress, current emotional benchmarks remain limited, as it is still unknown: (a)…
Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and…
Continuous Variational Autoencoders (VAEs) serve as the fundamental continuous tokenizer for modern neural audio generation systems, enabling high-fidelity reconstruction while providing a compact, smooth latent space for downstream generative priors. However, continuous VAEs face a fundamental conf…
The Speaker Diarization and Recognition (SDR) task aims to predict ``who spoke when and what
Although large language models (LLMs) excel in knowledge recall and reasoning, their static nature leads to outdated information as the real world evolves or when adapting to domain-specific knowledge, highlighting the need for effective knowledge injection. However, current research on knowledge in…
Nowadays, open-source large language models like LLaMA have emerged. Recent developments have incorporated supervised fine-tuning (SFT) and reinforcement learning fine-tuning (RLFT) to align these models with human goals. However, SFT methods treat all training data with mixed quality equally, while…
In recent years, many researchers have leveraged structural information from dependency trees to improve Named Entity Recognition (NER). Most of their methods take dependency-tree labels as input features for NER model training. However, such dependency information is not inherently provided in most…
This paper describes our best system and methodology for ADD 2022: The First Audio Deep Synthesis Detection Challenge[1]. The very same system was used for both two rounds of evaluation in Track 3.2 with similar training methodology. The first round of Track 3.2 data is generated from Text-to-Speech…
This paper presents the details of our system designed for the Task 1 of Multimodal Information Based Speech Processing (MISP) Challenge 2021. The purpose of Task 1 is to leverage both audio and video information to improve the environmental robustness of far-field wake word spotting. In the propose…
In this paper, we describe our speech generation system for the first Audio Deep Synthesis Detection Challenge (ADD 2022). Firstly, we build an any-to-many voice conversion (VC) system to convert source speech with arbitrary language content into target speaker’s fake speech. Then the converted spee…
Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages. It is observed that subtle literal changes often make an answerable question unanswerable, however, most MRC models fail to recognize such changes.…
The construction of an effective good speech recognition system typically requires large amounts of transcribed data, which is expensive to collect. To overcome this problem, many unsupervised pretraining methods have been proposed. Among these methods, Masked Predictive Coding achieved significant…
This paper introduces a new open-sourced Mandarin speech corpus, called DiDiSpeech. It consists of about 800 hours of speech data at 48kHz sampling rate from 6000 speakers and the corresponding texts. All speech data in the corpus is recorded in quiet environment and is suitable for various speech p…
This paper introduces an open source speech dataset, KeSpeech, which involves 1,542 hours of speech signals recorded by 27,237 speakers in 34 cities in China, and the pronunciation includes standard Mandarin and its 8 subdialects. The new dataset possesses several properties. Firstly, the dataset pr…
Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to learn a general and robust high-level representation for all…
Spectral mask based beamforming has showed competitive performance on multi-channel speech enhancement in recent years. However, such methods apply mask estimation on each channel and ensemble the masks from multiple channels into one for speech and noise covariance estimation. Spectral-spatial mask…
Abstractive text summarization is a challenging task, and one need to design a mechanism to effectively extract salient information from the source text and then generate a summary. A parsing process of the source text contains critical syntactic or semantic structures, which is useful to generate m…
Automatic Speech Verification (ASV) systems are highly vulnerable to spoofing attacks, and replay attack poses the greatest threat among various spoofing attacks. In this paper, we propose a novel multi-channel feature extraction method with attention-based adaptive filters (AAF). Original phase inf…
Most existing sequence labelling models rely on a fixed decomposition of a target sequence into a sequence of basic units. These methods suffer from two major drawbacks: $1$) the set of basic units is fixed, such as the set of words, characters or phonemes in speech recognition, and $2$) the decompo…
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of s…
Long short-term memory (LSTM) based acoustic modeling methods have recently been shown to give state-of-the-art performance on some speech recognition tasks. To achieve a further performance improvement, in this research, deep extensions on LSTM are investigated considering that deep hierarchical mo…
Long short-tem memory (LSTM) recurrent neural networks have been shown to give state-of-the-art performance on many speech recognition tasks. To achieve a further performance improvement, in this paper, maxout units are proposed to be integrated with the LSTM cells, considering those units have brou…