Related papers: A comparison of streaming models and data augmenta…
We investigate a monotonic multihead attention (MMA) by extending hard monotonic attention to Transformer-based automatic speech recognition (ASR) for online streaming applications. For streaming inference, all monotonic attention (MA)…
Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…
The Dual-Path Convolution Recurrent Network (DPCRN) was proposed to effectively exploit time-frequency domain information. By combining the DPRNN module with Convolution Recurrent Network (CRN), the DPCRN obtained a promising performance in…
Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…
In this paper, we propose an online attention mechanism, known as cumulative attention (CA), for streaming Transformer-based automatic speech recognition (ASR). Inspired by monotonic chunkwise attention (MoChA) and head-synchronous…
Mispronunciation detection and diagnosis (MDD) is a popular research focus in computer-aided pronunciation training (CAPT) systems. End-to-end (e2e) approaches are becoming dominant in MDD. However an e2e MDD model usually requires entire…
Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…
Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelization . In this paper, we propose a self-attention transducer…
Unification of automatic speech recognition (ASR) systems reduces development and maintenance costs, but training a single model to perform well in both offline and low-latency streaming settings remains challenging. We present a Unified…
RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text…
Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal…
Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…
Data augmentation has proven to be a promising prospect in improving the performance of deep learning models by adding variability to training data. In previous work with developing a noise robust acoustic-to-articulatory speech inversion…
End-to-end multi-talker speech recognition is an emerging research trend in the speech community due to its vast potential in applications such as conversation and meeting transcriptions. To the best of our knowledge, all existing research…
Deep learning has achieved substantial improvement on single-channel speech enhancement tasks. However, the performance of multi-layer perceptions (MLPs)-based methods is limited by the ability to capture the long-term effective history…
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…
Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work,…
Because of its streaming nature, recurrent neural network transducer (RNN-T) is a very promising end-to-end (E2E) model that may replace the popular hybrid model for automatic speech recognition. In this paper, we describe our recent…
The RNN-Transducers and improved attention-based encoder-decoder models are widely applied to streaming speech recognition. Compared with these two end-to-end models, the CTC model is more efficient in training and inference. However, it…