Related papers: High-precision Voice Search Query Correction via R…

The word error rate (WER) of an automatic speech recognition (ASR) system increases when a mismatch occurs between the training and the testing conditions due to the noise, etc. In this case, the acoustic information can be less reliable.…

Accurately finding the wrong words in the automatic speech recognition (ASR) hypothesis and recovering them well-founded is the goal of speech error correction. In this paper, we propose a non-autoregressive speech error correction method.…

Automatic speech recognition (ASR) is a relevant area in multiple settings because it provides a natural communication mechanism between applications and users. ASRs often fail in environments that use language specific to particular…

In embedding-matching acoustic-to-word (A2W) ASR, every word in the vocabulary is represented by a fixed-dimension embedding vector that can be added or removed independently of the rest of the system. The approach is potentially an elegant…

Automatic Speech Recognition (ASR) systems introduce word errors, which often confuse punctuation prediction models, turning punctuation restoration into a challenging task. These errors usually take the form of homonyms. We show how…

Interacting with a speech interface to query a Question Answering (QA) system is becoming increasingly popular. Typically, QA systems rely on passage retrieval to select candidate contexts and reading comprehension to extract the final…

Text encodings from automatic speech recognition (ASR) transcripts and audio representations have shown promise in speech emotion recognition (SER) ever since. Yet, it is challenging to explain the effect of each information stream on the…

Language models play a central role in automatic speech recognition (ASR), yet most methods rely on text-only models unaware of ASR error patterns. Recently, large language models (LLMs) have been applied to ASR correction, but introduce…

Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval…

End-to-end (E2E) Automatic Speech Recognition (ASR) models are trained using paired audio-text samples that are expensive to obtain, since high-quality ground-truth data requires human annotators. Voice search applications, such as digital…

With the development of deep learning, automatic speech recognition (ASR) has made significant progress. To further enhance the performance of ASR, revising recognition results is one of the lightweight but efficient manners. Various…

Error correction is widely used in automatic speech recognition (ASR) to post-process the generated sentence, and can further reduce the word error rate (WER). Although multiple candidates are generated by an ASR system through beam search,…

Accurate recognition of slot values such as domain specific words or named entities by automatic speech recognition (ASR) systems forms the core of the Goal-oriented Dialogue Systems. Although it is a critical step with direct impact on…

Neural speaker embeddings encode the speaker's speech characteristics through a DNN model and are prevalent for speaker verification tasks. However, few studies have investigated the usage of neural speaker embeddings for an ASR system. In…

Aiming at reducing the reliance on expensive human annotations, data synthesis for Automatic Speech Recognition (ASR) has remained an active area of research. While prior work mainly focuses on synthetic speech generation for ASR data…

Speech enhancement (SE) systems are typically evaluated using a variety of instrumental metrics. The use of automatic speech recognition (ASR) systems to evaluate SE performance is common in literature, usually in terms of word error rate…

In recent years, end-to-end automatic speech recognition (ASR) systems have proven themselves remarkably accurate and performant, but these systems still have a significant error rate for entity names which appear infrequently in their…

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

Building an accurate automatic speech recognition (ASR) system requires a large dataset that contains many hours of labeled speech samples produced by a diverse set of speakers. The lack of such open free datasets is one of the main issues…