Related papers: An analysis of incorporating an external language …
End-to-end models have achieved impressive results on the task of automatic speech recognition (ASR). For low-resource ASR tasks, however, labeled data can hardly satisfy the demand of end-to-end models. Self-supervised acoustic…
Training a conventional automatic speech recognition (ASR) system to support multiple languages is challenging because the sub-word unit, lexicon and word inventories are typically language specific. In contrast, sequence-to-sequence models…
Internal Language Model Estimation (ILME) based language model (LM) fusion has been shown significantly improved recognition results over conventional shallow fusion in both intra-domain and cross-domain speech recognition tasks. In this…
Sequence-to-sequence models have recently become very popular for tackling handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging problem. The main…
We present memory-based learning approaches to shallow parsing and apply these to five tasks: base noun phrase identification, arbitrary base phrase recognition, clause detection, noun phrase parsing and full parsing. We use feature…
We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…
Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…
The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…
Hybrid Autoregressive Transducer (HAT) is a recently proposed end-to-end acoustic model that extends the standard Recurrent Neural Network Transducer (RNN-T) for the purpose of the external language model (LM) fusion. In HAT, the blank…
Streaming processing of speech audio is required for many contemporary practical speech recognition tasks. Even with the large corpora of manually transcribed speech data available today, it is impossible for such corpora to cover…
Attention-based end-to-end models such as Listen, Attend and Spell (LAS), simplify the whole pipeline of traditional automatic speech recognition (ASR) systems and become popular in the field of speech recognition. In previous work,…
In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for…
Recently sequence-to-sequence models have started to achieve state-of-the-art performance on standard speech recognition tasks when processing audio data in batch mode, i.e., the complete audio data is available when starting processing.…
Segmentation for continuous Automatic Speech Recognition (ASR) has traditionally used silence timeouts or voice activity detectors (VADs), which are both limited to acoustic features. This segmentation is often overly aggressive, given that…
Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the speech domain is still a relatively unexplored topic, with…
Artefacts that serve to distinguish bona fide speech from spoofed or deepfake speech are known to reside in specific subbands and temporal segments. Various approaches can be used to capture and model such artefacts, however, none works…
We present our transducer model on Librispeech. We study variants to include an external language model (LM) with shallow fusion and subtract an estimated internal LM. This is justified by a Bayesian interpretation where the transducer…
We address text-assisted speech intelligibility prediction for hearing-impaired listeners in CPC3. Although the target is a sentence-level percentage, it is determined by reference-word recognition outcomes. We formulate prediction as…
Acoustic-to-word (A2W) end-to-end automatic speech recognition (ASR) systems have attracted attention because of an extremely simplified architecture and fast decoding. To alleviate data sparseness issues due to infrequent words, the…
Automatic speech recognition can potentially benefit from the lip motion patterns, complementing acoustic speech to improve the overall recognition performance, particularly in noise. In this paper we propose an audio-visual fusion strategy…