Related papers: Sentence-Select: Large-Scale Language Model Data S…
Language models (LMs) significantly improve the recognition accuracy of end-to-end (E2E) models on words rarely seen during training, when used in either the shallow fusion or the rescoring setups. In this work, we introduce LMs in the…
Attention-based sequence-to-sequence models for automatic speech recognition jointly train an acoustic model, language model, and alignment mechanism. Thus, the language model component is only trained on transcribed audio-text pairs. This…
Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…
We address the problem of language model customization in applications where the ASR component needs to manage domain-specific terminology; although current state-of-the-art speech recognition technology provides excellent results for…
Low-frequency words place a major challenge for automatic speech recognition (ASR). The probabilities of these words, which are often important name entities, are generally under-estimated by the language model (LM) due to their limited…
There are more than 7,000 languages around the world, and current Large Language Models (LLMs) only support hundreds of languages. Dictionary-based prompting methods can enhance translation on them, but most methods use all the available…
Automatic speech recognition systems have undoubtedly advanced with the integration of multilingual and multitask models such as Whisper, which have shown a promising ability to understand and process speech across a wide range of…
Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…
This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…
Most state-of-the-art speech systems are using Deep Neural Networks (DNNs). Those systems require a large amount of data to be learned. Hence, learning state-of-the-art frameworks on under-resourced speech languages/problems is a difficult…
Best-performing speech models are trained on large amounts of data in the language they are meant to work for. However, most languages have sparse data, making training models challenging. This shortage of data is even more prevalent in…
Deep biasing for the Transducer can improve the recognition performance of rare words or contextual entities, which is essential in practical applications, especially for streaming Automatic Speech Recognition (ASR). However, deep biasing…
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…
Despite the success of end-to-end automatic speech recognition (ASR) models, challenges persist in recognizing rare, out-of-vocabulary words - including named entities (NE) - and in adapting to new domains using only text data. This work…
In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt. This is accomplished by fine-tuning a pre-trained,…
In real-world applications, automatic speech recognition (ASR) systems must handle overlapping speech from multiple speakers and recognize rare words like technical terms. Traditional methods address multi-talker ASR and contextual biasing…
LLM-based automatic speech recognition models demonstrate strong performance by connecting audio encoders and LLMs. However, data scarcity of paired speech and transcription often hinders their adaptation to new domains, making text-only…
Single-word Automatic Speech Recognition (ASR) is a challenging task due to the lack of linguistic context and sensitivity to noise, pronunciation variation, and channel artifacts, especially in low-resource, communication-critical domains…
Language models (LMs) have been commonly adopted to boost the performance of automatic speech recognition (ASR) particularly in domain adaptation tasks. Conventional way of LM training treats all the words in corpora equally, resulting in…
Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…