相关论文: Cascaded Cross-Modal Transformer for Audio-Textual…

Recent foundational models, SSAST, EAT, HuBERT, Qwen-Audio, and Audio Flamingo, achieve top-tier results across standard audio benchmarks but are limited by fixed input rates and durations, hindering their reusability. This paper introduces…

Voice conversion refers to transferring speaker identity with well-preserved content. Better disentanglement of speech representations leads to better voice conversion. Recent studies have found that phonetic information from input audio…

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks,…

End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated, "clean" datasets. This overlooks critical real-world challenges, such as morphological robustness to…

Conditional coding has lately emerged as the mainstream approach to learned video compression. However, a recent study shows that it may perform worse than residual coding when the information bottleneck arises. Conditional residual coding…

Recently, end-to-end speech recognition with a hybrid model consisting of the connectionist temporal classification(CTC) and the attention encoder-decoder achieved state-of-the-art results. In this paper, we propose a novel CTC decoder…

Code-switching speech recognition (CSSR) transcribes speech that switches between multiple languages or dialects within a single sentence. The main challenge in this task is that different languages often have similar pronunciations, making…

Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually generate the sequence results token by token from left to right,…

Approximately half of the world's population is multilingual, making multilingual ASR (MASR) essential. Deploying multiple monolingual models is challenging when the ground-truth language is unknown in advance. This motivates research…

Multilingual models for Automatic Speech Recognition (ASR) are attractive as they have been shown to benefit from more training data, and better lend themselves to adaptation to under-resourced languages. However, initialisation from…

We propose a method named AudioFormer,which learns audio feature representations through the acquisition of discrete acoustic codes and subsequently fine-tunes them for audio classification tasks. Initially,we introduce a novel perspective…

State-of-the-art non-autoregressive text-to-speech (TTS) models based on FastSpeech 2 can efficiently synthesise high-fidelity and natural speech. For expressive speech datasets however, we observe characteristic audio distortions. We…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

Emotion recognition is a fundamental component of next-generation human-computer interaction (HCI), enabling machines to perceive, understand, and respond to users' affective states. However, existing systems often rely on single-modality…

We propose a novel Patched Multi-Condition Training (pMCT) method for robust Automatic Speech Recognition (ASR). pMCT employs Multi-condition Audio Modification and Patching (MAMP) via mixing {\it patches} of the same utterance extracted…

Audio Visual Scene-aware Dialog (AVSD) is the task of generating a response for a question with a given scene, video, audio, and the history of previous turns in the dialog. Existing systems for this task employ the transformers or…

Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…

End-to-end models are favored in automatic speech recognition (ASR) because of its simplified system structure and superior performance. Among these models, recurrent neural network transducer (RNN-T) has achieved significant progress in…

Multilingual automatic speech recognition (ASR) models have shown great promise in recent years because of the simplified model training and deployment process. Conventional methods either train a universal multilingual model without taking…

In this paper, we propose a novel speech emotion recognition model called Cross Attention Network (CAN) that uses aligned audio and text signals as inputs. It is inspired by the fact that humans recognize speech as a combination of…