Related papers: Exploring Retraining-Free Speech Recognition for I…
In this study, we delve into the efficacy of transformers within pre-trained language models (PLMs) when repurposed as encoders for Automatic Speech Recognition (ASR). Our underlying hypothesis posits that, despite being initially trained…
Achieving high accuracy with end-to-end speech recognizers requires careful parameter initialization prior to training. Otherwise, the networks may fail to find a good local optimum. This is particularly true for online networks, such as…
We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model is adapted from a speech foundation model trained on a large quantity of…
Improving the accuracy of single-channel automatic speech recognition (ASR) in noisy conditions is challenging. Strong speech enhancement front-ends are available, however, they typically require that the ASR model is retrained to cope with…
We explore the ability of large language models (LLMs) to act as speech recognition post-processors that perform rescoring and error correction. Our first focus is on instruction prompting to let LLMs perform these task without fine-tuning,…
State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when…
Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of…
Although n-gram language models (LMs) have been outperformed by the state-of-the-art neural LMs, they are still widely used in speech recognition due to its high efficiency in inference. In this paper, we demonstrate that n-gram LM can be…
Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to…
Despite the rapid progress of end-to-end (E2E) automatic speech recognition (ASR), it has been shown that incorporating external language models (LMs) into the decoding can further improve the recognition performance of E2E ASR systems. To…
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…
The goal of this paper is to simulate the benefits of jointly applying active learning (AL) and semi-supervised training (SST) in a new speech recognition application. Our data selection approach relies on confidence filtering, and its…
The integration of Language Models (LMs) has proven to be an effective way to address domain shifts in speech recognition. However, these approaches usually require a significant amount of target domain text data for the training of LMs.…
In this paper, we propose a neural-based coding scheme in which an artificial neural network is exploited to automatically compress and decompress speech signals by a trainable approach. Having a two-stage training phase, the system can be…
In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from previous LLM-based ASR error correction methods, we propose a novel multi-stage…
Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM), pronunciation (PM) and language (LM) models into a single…
The advent of Large Language Models (LLM) has reformed the Automatic Speech Recognition (ASR). Prompting LLM with audio embeddings to generate transcriptions becomes the new state-of-the-art ASR. Despite LLMs being trained with an extensive…
Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g., speech…
Code-switching automatic speech recognition (ASR) aims to transcribe speech that contains two or more languages accurately. To better capture language-specific speech representations and address language confusion in code-switching ASR, the…
The advancement of multimodal large language models has accelerated the development of speech-to-speech interaction systems. While natural monolingual interaction has been achieved, we find existing models exhibit deficiencies in language…