Related papers: Fully Learnable Front-End for Multi-Channel Acoust…

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

This paper proposes a novel approach to pre-train encoder-decoder sequence-to-sequence (seq2seq) model with unpaired speech and transcripts respectively. Our pre-training method is divided into two stages, named acoustic pre-trianing and…

In automatic speech recognition (ASR), wideband (WB) and narrowband (NB) speech signals with different sampling rates typically use separate acoustic models. Therefore mixed-bandwidth (MB) acoustic modeling has important practical values…

One of the central skills that language learners need to practice is speaking the language. Currently, students in school do not get enough speaking opportunities and lack conversational practice. Recent advances in speech technology and…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

In this study, we develop the keyword spotting (KWS) and acoustic model (AM) components in a far-field speaker system. Specifically, we use teacher-student (T/S) learning to adapt a close-talk well-trained production AM to far-field by…

In this work, we propose a new automatic speech recognition (ASR) system based on feature learning and an end-to-end training procedure for air traffic control (ATC) systems. The proposed model integrates the feature learning block,…

We present a frontend for improving robustness of automatic speech recognition (ASR), that jointly implements three modules within a single model: acoustic echo cancellation, speech enhancement, and speech separation. This is achieved by…

Far-field speech recognition is a challenging task that conventionally uses signal processing beamforming to attack noise and interference problem. But the performance has been found usually limited due to heavy reliance on environmental…

Self-supervised learning (SSL) models have achieved considerable improvements in automatic speech recognition (ASR). In addition, ASR performance could be further improved if the model is dedicated to audio content information learning…

Neural front-ends represent a promising approach to feature extraction for automatic speech recognition (ASR) systems as they enable to learn specifically tailored features for different tasks. Yet, many of the existing techniques remain…

Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Recent literature has shown that a learned front end with multi-channel audio input can outperform traditional beam-forming algorithms for automatic speech recognition (ASR). In this paper, we present our study on multi-channel acoustic…

In Automatic Speech Recognition (ASR), teacher-student (T/S) training has shown to perform well for domain adaptation with small amount of training data. However, adaption without ground-truth labels is still challenging. A previous study…

This paper is a study of performance-efficiency trade-offs in pre-trained models for automatic speech recognition (ASR). We focus on wav2vec 2.0, and formalize several architecture designs that influence both the model performance and its…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

Multilingual end-to-end models have shown great improvement over monolingual systems. With the development of pre-training methods on speech, self-supervised multilingual speech representation learning like XLSR has shown success in…

In this paper, we present methods in deep multimodal learning for fusing speech and visual modalities for Audio-Visual Automatic Speech Recognition (AV-ASR). First, we study an approach where uni-modal deep networks are trained separately…