相关论文: How I Built ASR for Endangered Languages with a Sp…

We present improvements in automatic speech recognition (ASR) for Somali, a currently extremely under-resourced language. This forms part of a continuing United Nations (UN) effort to employ ASR-based keyword spotting systems to support…

The SENCOTEN language, spoken on the Saanich peninsula of southern Vancouver Island, is in the midst of vigorous language revitalization efforts to turn the tide of language loss as a result of colonial language policies. To support these…

One common approach for question answering over speech data is to first transcribe speech using automatic speech recognition (ASR) and then employ text-based retrieval-augmented generation (RAG) on the transcriptions. While this cascaded…

Automatic speech recognition (ASR) has the potential to substantially reduce manual annotation effort in child speech research by generating automatic transcriptions. However, obtaining reliably high-quality ASR transcriptions for child…

Although contextualized automatic speech recognition (ASR) systems are commonly used to improve the recognition of uncommon words, their effectiveness is hindered by the inherent limitations of speech-text data availability. To address this…

Automatic speech recognition (ASR) systems often need to be developed for extremely low-resource languages to serve end-uses such as audio content categorization and search. While universal phone recognition is natural to consider when no…

Automatic Speech Recognition (ASR) systems exhibit the best performance on speech that is similar to that on which it was trained. As such, underrepresented varieties including regional dialects, minority-speakers, and low-resource…

Despite tremendous progress in natural language processing using deep learning techniques in recent years, sign language production and comprehension has advanced very little. One critical barrier is the lack of largescale datasets…

Speech synthesis might hold the key to low-resource speech recognition. Data augmentation techniques have become an essential part of modern speech recognition training. Yet, they are simple, naive, and rarely reflect real-world conditions.…

Automatic Speech Recognition (ASR) has increasing utility in the modern world. There are a many ASR models available for languages with large amounts of training data like English. However, low-resource languages are poorly represented. In…

Automatic speech recognition (ASR) meets more informal and free-form input data as voice user interfaces and conversational agents such as the voice assistants such as Alexa, Google Home, etc., gain popularity. Conversational speech is both…

Streaming end-to-end automatic speech recognition (ASR) models are widely used on smart speakers and on-device applications. Since these models are expected to transcribe speech with minimal latency, they are constrained to be causal with…

Automatic Speech Recognition (ASR) is an integral component of modern technology, powering applications such as voice-activated assistants, transcription services, and accessibility tools. Yet ASR systems continue to struggle with the…

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

It is estimated that around 70 million people worldwide are affected by a speech disorder called stuttering. With recent advances in Automatic Speech Recognition (ASR), voice assistants are increasingly useful in our everyday lives. Many…

While supervised quality predictors for synthesized speech have demonstrated strong correlations with human ratings, their requirement for in-domain labeled training data hinders their generalization ability to new domains. Unsupervised…

Expanding the language coverage of speech technology has the potential to improve access to information for many more people. However, current speech technology is restricted to about one hundred languages which is a small fraction of the…

Nowadays, the main problem of deep learning techniques used in the development of automatic speech recognition (ASR) models is the lack of transcribed data. The goal of this research is to propose a new data augmentation method to improve…

This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual…

Most recent speech recognition models rely on large supervised datasets, which are unavailable for many low-resource languages. In this work, we present a speech recognition pipeline that does not require any audio for the target language.…