Related papers: CASS-NAT: CTC Alignment-based Single Step Non-auto…

Transformers have recently dominated the ASR field. Although able to yield good performance, they involve an autoregressive (AR) decoder to generate tokens one by one, which is computationally inefficient. To speed up inference,…

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Fully non-autoregressive neural machine translation (NAT) is proposed to simultaneously predict tokens with single forward of neural networks, which significantly reduces the inference latency at the expense of quality drop compared to the…

This paper proposes a novel label-synchronous speech-to-text alignment technique for automatic speech recognition (ASR). The speech-to-text alignment is a problem of splitting long audio recordings with un-aligned transcripts into…

RNN-Transducer (RNN-T) is a widely adopted architecture in speech recognition, integrating acoustic and language modeling in an end-to-end framework. However, the RNN-T predictor tends to over-rely on consecutive word dependencies in…

Because of predicting all the target tokens in parallel, the non-autoregressive models greatly improve the decoding efficiency of speech recognition compared with traditional autoregressive models. In this work, we present dynamic alignment…

This paper integrates a voice activity detection (VAD) function with end-to-end automatic speech recognition toward an online speech interface and transcribing very long audio recordings. We focus on connectionist temporal classification…

The success of retrieval-augmented language models in various natural language processing (NLP) tasks has been constrained in automatic speech recognition (ASR) applications due to challenges in constructing fine-grained audio-text…

We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR). The model consists of a TitaNet based speaker embedding module, a Conformer…

This paper investigates four types of cross-utterance speech contexts modeling approaches for streaming and non-streaming Conformer-Transformer (C-T) ASR systems: i) input audio feature concatenation; ii) cross-utterance Encoder embedding…

Non-native speech causes automatic speech recognition systems to degrade in performance. Past strategies to address this challenge have considered model adaptation, accent classification with a model selection, alternate pronunciation…

Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in…

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information.…

Temporal connectionist temporal classification (CTC)-based automatic speech recognition (ASR) is one of the most successful end to end (E2E) ASR frameworks. However, due to the token independence assumption in decoding, an external language…

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT)…

Accent Conversion (AC) seeks to change the accent of speech from one (source) to another (target) while preserving the speech content and speaker identity. However, many AC approaches rely on source-target parallel speech data. We propose a…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

The success of self-attention in NLP has led to recent applications in end-to-end encoder-decoder architectures for speech recognition. Separately, connectionist temporal classification (CTC) has matured as an alignment-free,…

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Connectionist Temporal Classification has recently attracted a lot of interest as it offers an elegant approach to building acoustic models (AMs) for speech recognition. The CTC loss function maps an input sequence of observable feature…