Related papers: Word Level Timestamp Generation for Automatic Spee…

Recent research on word-level confidence estimation for speech recognition systems has primarily focused on lightweight models known as Confidence Estimation Modules (CEMs), which rely on hand-engineered features derived from Automatic…

This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing…

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

In this paper, we propose an incremental learning method for end-to-end Automatic Speech Recognition (ASR) which enables an ASR system to perform well on new tasks while maintaining the performance on its originally learned ones. To…

Despite recent advances, Automatic Speech Recognition (ASR) systems are still far from perfect. Typical errors include acronyms, named entities, and domain-specific special words for which little or no labeled data is available. To address…

Conventional ASR systems use frame-level phoneme posterior to conduct force-alignment~(FA) and provide timestamps, while end-to-end ASR systems especially AED based ones are short of such ability. This paper proposes to perform timestamp…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a…

Recent advancement in deep learning encouraged developing large automatic speech recognition (ASR) models that achieve promising results while ignoring computational and memory constraints. However, deploying such models on low resource…

We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder's cross-attention scores. We…

Forced alignment (FA) predicts start and end timestamps for words or characters in speech, but existing methods are language-specific and prone to cumulative temporal shifts. The multilingual speech understanding and long-sequence…

For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training…

End-to-end (E2E) models are often being accompanied by language models (LMs) via shallow fusion for boosting their overall quality as well as recognition of rare words. At the same time, several prior works show that LMs are susceptible 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…

Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We…

Contextual information plays a crucial role in speech recognition technologies and incorporating it into the end-to-end speech recognition models has drawn immense interest recently. However, previous deep bias methods lacked explicit…

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…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Many multilingual NLP applications need to translate words between different languages, but cannot afford the computational expense of inducing or applying a full translation model. For these applications, we have designed a fast algorithm…

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…