Related papers: Speech enhancement aided end-to-end multi-task lea…
Automatic speech recognition (ASR) technologies have been significantly advanced in the past few decades. However, recognition of overlapped speech remains a highly challenging task to date. To this end, multi-channel microphone array data…
Supervised speech enhancement methods have been very successful. However, in practical scenarios, there is a lack of clean speech, and self-supervised learning-based (SSL) speech enhancement methods that offer comparable enhancement…
Speaker diarization, the process of identifying "who spoke when" in audio recordings, is essential for understanding classroom dynamics. However, classroom settings present distinct challenges, including poor recording quality, high levels…
State-of-the-art deep-learning-based voice activity detectors (VADs) are often trained with anechoic data. However, real acoustic environments are generally reverberant, which causes the performance to significantly deteriorate. To mitigate…
The multi-decoder (MD) end-to-end speech translation model has demonstrated high translation quality by searching for better intermediate automatic speech recognition (ASR) decoder states as hidden intermediates (HI). It is a two-pass…
To cope with reverberation and noise in single channel acoustic scenarios, typical supervised deep neural network~(DNN)-based techniques learn a mapping from reverberant and noisy input features to a user-defined target. Commonly used…
Multi-speaker automatic speech recognition (ASR) is crucial for many real-world applications, but it requires dedicated modeling techniques. Existing approaches can be divided into modular and end-to-end methods. Modular approaches separate…
Various neural network-based approaches have been proposed for more robust and accurate voice activity detection (VAD). Manual design of such neural architectures is an error-prone and time-consuming process, which prompted the development…
In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming on-device speech recognition system, such that it only…
Accurate recognition of cocktail party speech containing overlapping speakers, noise and reverberation remains a highly challenging task to date. Motivated by the invariance of visual modality to acoustic signal corruption, an audio-visual…
In the realm of digital audio processing, Voice Activity Detection (VAD) plays a pivotal role in distinguishing speech from non-speech elements, a task that becomes increasingly complex in noisy environments. This paper details the…
This paper aims at eliminating the interfering speakers' speech, additive noise, and reverberation from the noisy multi-talker speech mixture that benefits automatic speech recognition (ASR) backend. While the recently proposed Weighted…
The Transformer has shown impressive performance in automatic speech recognition. It uses the encoder-decoder structure with self-attention to learn the relationship between the high-level representation of the source inputs and embedding…
Research on multilingual speech recognition remains attractive yet challenging. Recent studies focus on learning shared structures under the multi-task paradigm, in particular a feature sharing structure. This approach has been found…
Recently, the deep-belief-networks (DBN) based voice activity detection (VAD) has been proposed. It is powerful in fusing the advantages of multiple features, and achieves the state-of-the-art performance. However, the deep layers of the…
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been…
Speech enhancement in audio-only settings remains challenging, particularly in the presence of interfering speakers. This paper presents a simple yet effective real-time audio-visual speech enhancement (AVSE) system, RAVEN, which isolates…
Multimodal speech recognition aims to improve the performance of automatic speech recognition (ASR) systems by leveraging additional visual information that is usually associated to the audio input. While previous approaches make crucial…
Mispronunciation detection and diagnosis (MDD) technology is a key component of computer-assisted pronunciation training system (CAPT). In the field of assessing the pronunciation quality of constrained speech, the given transcriptions can…
Voice activity detection is the task of detecting speech regions in a given audio stream or recording. First, we design a neural network combining trainable filters and recurrent layers to tackle voice activity detection directly from the…