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

Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when. The task of assigning words to speakers is typically addressed by merging the outputs of two separate…

Non-reference speech quality models are important for a growing number of applications. The VoiceMOS 2022 challenge provided a dataset of synthetic voice conversion and text-to-speech samples with subjective labels. This study looks at the…

Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…

Automatic speech recognition (ASR) systems have achieved strong performance on general transcription tasks. However, they continue to struggle with recognizing rare named entities and adapting to domain mismatches. In contrast, large…

High quality transcription data is crucial for training automatic speech recognition (ASR) systems. However, the existing industry-level data collection pipelines are expensive to researchers, while the quality of crowdsourced transcription…

We describe a system that generates speaker-annotated transcripts of meetings by using a virtual microphone array, a set of spatially distributed asynchronous recording devices such as laptops and mobile phones. The system is composed of…

A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…

Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening study on audio deepfake perception to date, collecting 35,532 judgments from 1,768…

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…

A major hurdle on the road to conversational interfaces is the difficulty in collecting data that maps language utterances to logical forms. One prominent approach for data collection has been to automatically generate pseudo-language…

Given recent advances in generative AI technology, a key question is how large language models (LLMs) can enhance acoustic modeling tasks using text decoding results from a frozen, pretrained automatic speech recognition (ASR) model. To…

Whisper fails to correctly transcribe dementia speech because persons with dementia (PwDs) often exhibit irregular speech patterns and disfluencies such as pauses, repetitions, and fragmented sentences. It was trained on standard speech and…

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…

Personality have been found to predict many life outcomes, and there have been huge interests on automatic personality recognition from a speaker's utterance. Previously, we achieved accuracies between 37%-44% for three-way classification…

We investigate the problem of manually correcting errors from an automatic speech transcript in a cost-sensitive fashion. This is done by specifying a fixed time budget, and then automatically choosing location and size of segments for…

Displaying a written transcript of what a human said (i.e. producing an "automatic speech recognition transcript") is a common feature for smartphone vocal assistants: the utterance produced by a human speaker (e.g. a question) is displayed…

Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by…

The current public datasets for speech recognition (ASR) tend not to focus specifically on the fairness aspect, such as performance across different demographic groups. This paper introduces a novel dataset, Fair-Speech, a publicly released…

Recognition systems are commonly designed to authenticate users at the access control levels of a system. A number of voice recognition methods have been developed using a pitch estimation process which are very vulnerable in low Signal to…

Automatic transcriptions of consumer-generated multi-media content such as "Youtube" videos still exhibit high word error rates. Such data typically occupies a very broad domain, has been recorded in challenging conditions, with cheap…