Related papers: A Comparative Study on Non-Autoregressive Modeling…

Non-autoregressive mechanisms can significantly decrease inference time for speech transformers, especially when the single step variant is applied. Previous work on CTC alignment-based single step non-autoregressive transformer (CASS-NAT)…

Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a non-autoregressive neural text-to-speech model augmented…

We present a novel approach to end-to-end automatic speech recognition (ASR) that utilizes pre-trained masked language models (LMs) to facilitate the extraction of linguistic information. The proposed models, BERT-CTC and BECTRA, are…

Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…

Conventional keyword search systems operate on automatic speech recognition (ASR) outputs, which causes them to have a complex indexing and search pipeline. This has led to interest in ASR-free approaches to simplify the search procedure.…

End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training, as well as heavyweight computation for inference. Of course, this impedes…

Non-autoregressive models greatly improve decoding speed over typical sequence-to-sequence models, but suffer from degraded performance. Infilling and iterative refinement models make up some of this gap by editing the outputs of a…

Named entity recognition (NER) is among SLU tasks that usually extract semantic information from textual documents. Until now, NER from speech is made through a pipeline process that consists in processing first an automatic speech…

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data…

Non-autoregressive (NAR) language models offer notable efficiency in text generation by circumventing the sequential bottleneck of autoregressive decoding. However, accurately modeling dependencies in discrete sequences remains challenging…

State-of-the-art end-to-end automatic speech recognition (ASR) extracts acoustic features from input speech signal every 10 ms which corresponds to a frame rate of 100 frames/second. In this report, we investigate the use of high-frame-rate…

AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token image generation mechanism remains computationally intensive…

Recent advances in large language models (LLMs) have attracted significant interest in extending their capabilities to multimodal scenarios, particularly for speech-to-speech conversational systems. However, existing multimodal models…

Improving the representation of contextual information is key to unlocking the potential of end-to-end (E2E) automatic speech recognition (ASR). In this work, we present a novel and simple approach for training an ASR context mechanism with…

Encoder-decoder based sequence-to-sequence models have demonstrated state-of-the-art results in end-to-end automatic speech recognition (ASR). Recently, the transformer architecture, which uses self-attention to model temporal context…

Mandarin-English code-switching (CS) is frequently used among East and Southeast Asian people. However, the intra-sentence language switching of the two very different languages makes recognizing CS speech challenging. Meanwhile, the recent…

End-to-end neural automatic speech recognition systems achieved recently state-of-the-art results, but they require large datasets and extensive computing resources. Transfer learning has been proposed to overcome these difficulties even…

Combining end-to-end speech translation (ST) and non-autoregressive (NAR) generation is promising in language and speech processing for their advantages of less error propagation and low latency. In this paper, we investigate the potential…

End-to-end automatic speech recognition (ASR) commonly transcribes audio signals into sequences of characters while its performance is evaluated by measuring the word-error rate (WER). This suggests that predicting sequences of words…

Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…