相关论文: Two-stage training method for Japanese electrolary…

Performance degradation of an Automatic Speech Recognition (ASR) system is commonly observed when the test acoustic condition is different from training. Hence, it is essential to make ASR systems robust against various environmental…

In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target. To…

Linear sequence modeling approaches, such as linear attention, provide advantages like linear-time training and constant-memory inference over sequence lengths. However, existing sequence parallelism (SP) methods are either not optimized…

Using unsupervised learning to disentangle speech into content, rhythm, pitch, and timbre for voice conversion has become a hot research topic. Existing works generally take into account disentangling speech components through human-crafted…

Recently, the end-to-end approach has proven its efficacy in monaural multi-speaker speech recognition. However, high word error rates (WERs) still prevent these systems from being used in practical applications. On the other hand, the…

Direct speech-to-speech translation (S2ST), in which all components are trained jointly, is an attractive alternative to cascaded systems because it offers a simpler pipeline and lower inference latency. However, direct S2ST models require…

This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement…

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

We present improvements to speaker diarization in the two-stage end-to-end neural diarization with vector clustering (EEND-VC) framework. The first stage employs a Conformer-based EEND model with WavLM features to infer frame-level speaker…

Recently, deep learning-based Text-to-Speech (TTS) systems have achieved high-quality speech synthesis results. Recurrent neural networks have become a standard modeling technique for sequential data in TTS systems and are widely used.…

Joint punctuated and normalized automatic speech recognition (ASR) aims at outputing transcripts with and without punctuation and casing. This task remains challenging due to the lack of paired speech and punctuated text data in most ASR…

Traditional voice conversion (VC) methods typically attempt to separate speaker identity and linguistic information into distinct representations, which are then combined to reconstruct the audio. However, effectively disentangling these…

Recently, the end-to-end approach has been successfully applied to multi-speaker speech separation and recognition in both single-channel and multichannel conditions. However, severe performance degradation is still observed in the…

End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising…

The process of reconstructing missing parts of speech audio from context is called speech in-painting. Human perception of speech is inherently multi-modal, involving both audio and visual (AV) cues. In this paper, we introduce and study a…

Extending the context length (i.e., the maximum supported sequence length) of LLMs is of paramount significance. To facilitate long context training of LLMs, sequence parallelism has emerged as an essential technique, which scatters each…

End-to-end models are fast replacing the conventional hybrid models in automatic speech recognition. Transformer, a sequence-to-sequence model, based on self-attention popularly used in machine translation tasks, has given promising results…

End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module. However, paired utterance…