相关论文: "Sorry, I Didn't Catch That": How Speech Models Mi…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both expensive and limited by the speed of manual transcription.…

Despite advances in Automatic Speech Recognition (ASR), transcription errors persist and require manual correction. Confidence scores, which indicate the certainty of ASR results, could assist users in identifying and correcting errors.…

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…

Mismatched transcriptions have been proposed as a mean to acquire probabilistic transcriptions from non-native speakers of a language.Prior work has demonstrated the value of these transcriptions by successfully adapting cross-lingual ASR…

We study the effectiveness of several techniques to personalize end-to-end speech models and improve the recognition of proper names relevant to the user. These techniques differ in the amounts of user effort required to provide…

Stuttering affects approximately 1% of the global population, impacting communication and quality of life. While recent advances in deep learning have pushed the boundaries of automatic speech dysfluency detection, rule-based approaches…

Syntactic natural language parsers have shown themselves to be inadequate for processing highly-ambiguous large-vocabulary text, as is evidenced by their poor performance on domains like the Wall Street Journal, and by the movement away…

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

ASR models often suffer from a long-form deletion problem where the model predicts sequential blanks instead of words when transcribing a lengthy audio (in the order of minutes or hours). From the perspective of a user or downstream system…

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on…

This paper explores the integration of Large Language Models (LLMs) into Automatic Speech Recognition (ASR) systems to improve transcription accuracy. The increasing sophistication of LLMs, with their in-context learning capabilities and…

In speech recognition problems, data scarcity often poses an issue due to the willingness of humans to provide large amounts of data for learning and classification. In this work, we take a set of 5 spoken Harvard sentences from 7 subjects…

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…

Dysfluencies and variations in speech pronunciation can severely degrade speech recognition performance, and for many individuals with moderate-to-severe speech disorders, voice operated systems do not work. Current speech recognition…

Automated speech recognition (ASR) models have gained prominence for applications such as captioning, speech translation, and live transcription. This paper studies Whisper and two model variants: one optimized for live speech streaming and…

To transcribe speech, automatic speech recognition systems use statistical methods, particularly hidden Markov model and N-gram models. Although these techniques perform well and lead to efficient systems, they approach their maximum…

Diarization is a crucial component in meeting transcription systems to ease the challenges of speech enhancement and attribute the transcriptions to the correct speaker. Particularly in the presence of overlapping or noisy speech, these…

Many consumer speech recognition systems are not tuned for people with speech disabilities, resulting in poor recognition and user experience, especially for severe speech differences. Recent studies have emphasized interest in personalized…

Spoken language understanding (SLU) system usually consists of various pipeline components, where each component heavily relies on the results of its upstream ones. For example, Intent detection (ID), and slot filling (SF) require its…