Related papers: Recognize Foreign Low-Frequency Words with Similar…
Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…
We propose a new method of generating meaningful embeddings for speech, changes to four commonly used meta learning approaches to enable them to perform keyword spotting in continuous signals and an approach of combining their outcomes into…
Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we…
A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose…
Recent advancements in supervised automatic speech recognition (ASR) have achieved remarkable performance, largely due to the growing availability of large transcribed speech corpora. However, most languages lack sufficient paired speech…
Existing research suggests that automatic speech recognition (ASR) models can benefit from additional contexts (e.g., contact lists, user specified vocabulary). Rare words and named entities can be better recognized with contexts. In this…
Neural sequence-to-sequence systems deliver state-of-the-art performance for automatic speech recognition (ASR). When using appropriate modeling units, e.g., byte-pair encoded characters, these systems are in principal open vocabulary…
State-of-the-art automatic speech recognition (ASR) systems struggle with the lack of data for rare accents. For sufficiently large datasets, neural engines tend to outshine statistical models in most natural language processing problems.…
Cross-lingual retrieval aims to retrieve relevant text across languages. Current methods typically achieve cross-lingual retrieval by learning language-agnostic text representations in word or sentence level. However, how to learn phrase…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…
Contextual ASR or hotword customization holds substantial practical value. Despite the impressive performance of current end-to-end (E2E) automatic speech recognition (ASR) systems, they often face challenges in accurately recognizing rare…
We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…
The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…
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…
The problem of rare and unknown words is an important issue that can potentially influence the performance of many NLP systems, including both the traditional count-based and the deep learning models. We propose a novel way to deal with the…
Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models.…
There is a lack of an evaluation methodology that estimates the extent to which large language models (LLMs) use code-switching (CS) in the same way as bilinguals. Existing methods do not have wide language coverage, fail to account for the…
In this paper, we present a series of complementary approaches to improve the recognition of underrepresented named entities (NE) in hybrid ASR systems without compromising overall word error rate performance. The underrepresented words…
We describe a new framework for distilling information from word lattices to improve the accuracy of speech recognition and obtain a more perspicuous representation of a set of alternative hypotheses. In the standard MAP decoding approach…
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…