Related papers: Improving Noisy Student Training on Non-target Dom…

Recent advances in automatic speech recognition (ASR) have combined speech encoders with large language models (LLMs) through projection, forming Speech LLMs with strong performance. However, adapting them to new domains remains…

Speech Large Language Models (Speech LLMs) have emerged as a crucial paradigm in recent years, extending the capabilities of traditional LLMs to speech tasks such as automatic speech recognition (ASR) and spoken dialogue modeling. However,…

Recently, deep neural network (DNN)-based speech enhancement (SE) systems have been used with great success. During training, such systems require clean speech data - ideally, in large quantity with a variety of acoustic conditions, many…

Automatic Speech Recognition (ASR) systems generally do not produce punctuated transcripts. To make transcripts more readable and follow the expected input format for downstream language models, it is necessary to add punctuation marks. In…

Although state-of-the-art Speech Foundational Models can produce high-quality text pseudo-labels, applying Semi-Supervised Learning (SSL) for in-the-wild real-world data remains challenging due to its richer and more complex acoustics…

Neural machine translation models have shown to achieve high quality when trained and fed with well structured and punctuated input texts. Unfortunately, the latter condition is not met in spoken language translation, where the input is…

This paper describes AaltoASR's speech recognition system for the INTERSPEECH 2020 shared task on Automatic Speech Recognition (ASR) for non-native children's speech. The task is to recognize non-native speech from children of various age…

Contextual biasing improves automatic speech recognition (ASR) by integrating external knowledge, such as user-specific phrases or entities, during decoding. In this work, we use an attention-based biasing decoder to produce scores for…

We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…

This paper presents techniques and findings for improving the performance of low-resource speech to text translation (ST). We conducted experiments on both simulated and real-low resource setups, on language pairs English - Portuguese, and…

When there is a mismatch between the training and test domains, current speech recognition systems show significant performance degradation. Self-training methods, such as noisy student teacher training, can help address this and enable the…

Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child…

Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…

Lately, the self-attention mechanism has marked a new milestone in the field of automatic speech recognition (ASR). Nevertheless, its performance is susceptible to environmental intrusions as the system predicts the next output symbol…

Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…

Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with…

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In…

Masked speech modeling (MSM) methods such as wav2vec2 or w2v-BERT learn representations over speech frames which are randomly masked within an utterance. While these methods improve performance of Automatic Speech Recognition (ASR) systems,…

Supervised training of speech recognition models requires access to transcribed audio data, which often is not possible due to confidentiality issues. Our approach to this problem is to generate synthetic audio from a text-only corpus using…

Large Language Models (LLMs) have showcased exceptional performance across diverse NLP tasks, and their integration with speech encoder is rapidly emerging as a dominant trend in the Automatic Speech Recognition (ASR) field. Previous works…