相关论文: Improving the Training Recipe for a Robust Conform…

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality--It…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Modern speaker verification (SV) systems typically demand expensive storage and computing resources, thereby hindering their deployment on mobile devices. In this paper, we explore adaptive neural network quantization for lightweight…

Spoken question answering (SQA) is challenging due to complex reasoning on top of the spoken documents. The recent studies have also shown the catastrophic impact of automatic speech recognition (ASR) errors on SQA. Therefore, this work…

This paper proposes an improved approach for open-set speaker identification based on pretrained speaker foundation models. Building upon the previous Speaker Reciprocal Points Learning framework (V1), we first introduce an enhanced…

We investigate continued pretraining (CPT) for adapting wav2vec2-bert-2.0 to Swahili automatic speech recognition (ASR). Our approach combines unlabeled audio with limited labeled data through pseudo-labeled CPT followed by supervised…

Current state-of-the-art automatic speaker verification (ASV) systems are vulnerable to presentation attacks, and several countermeasures (CMs), which distinguish bona fide trials from spoofing ones, have been explored to protect ASV.…

Edge-based automatic speech recognition (ASR) technologies are increasingly prevalent in the development of intelligent and personalized assistants. However, resource-constrained ASR models face significant challenges in adaptivity,…

Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…

This paper investigates the under-explored area of low-rank weight training for large-scale Conformer-based speech recognition models from scratch. Our study demonstrates the viability of this training paradigm for such models, yielding…

Sequence-to-sequence attention-based models on subword units allow simple open-vocabulary end-to-end speech recognition. In this work, we show that such models can achieve competitive results on the Switchboard 300h and LibriSpeech 1000h…

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…

The performances of the automatic speaker verification (ASV) systems degrade due to the reduction in the amount of speech used for enrollment and verification. Combining multiple systems based on different features and classifiers…

Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

Speech enhancement (SE) is usually required as a front end to improve the speech quality in noisy environments, while the enhanced speech might not be optimal for automatic speech recognition (ASR) systems due to speech distortion. On the…

Foundation ASR models often support many languages, e.g. 100 languages in Whisper. However, there has been limited work on integrating an additional, typically low-resource, language, while maintaining performance on the original language…

Automatic speech recognition (ASR) training can utilize multiple experts as teacher models, each trained on a specific domain or accent. Teacher models may be opaque in nature since their architecture may be not be known or their training…

Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from…

Spoofing-robust automatic speaker verification (SASV) seeks to build automatic speaker verification systems that are robust against both zero-effort impostor attacks and sophisticated spoofing techniques such as voice conversion (VC) and…