Related papers: Spontaneous Informal Speech Dataset for Punctuatio…
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…
Identifying mistakes (i.e., miscues) made while reading aloud is commonly approached post-hoc by comparing automatic speech recognition (ASR) transcriptions to the target reading text. However, post-hoc methods perform poorly when ASR…
In this paper, we propose MixSpeech, a simple yet effective data augmentation method based on mixup for automatic speech recognition (ASR). MixSpeech trains an ASR model by taking a weighted combination of two different speech features…
End-to-end speech-to-speech translation (S2ST) systems typically struggle with a critical data bottleneck: the scarcity of parallel speech-to-speech corpora. To overcome this, we introduce RosettaSpeech, a novel zero-shot framework trained…
Automatic speaker verification is susceptible to various manipulations and spoofing, such as text-to-speech synthesis, voice conversion, replay, tampering, adversarial attacks, and so on. We consider a new spoofing scenario called "Partial…
Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. However, publicly available SLU resources are limited. In this…
Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances. Most of the existing target-speaker ASR (TS-ASR) methods involve either training from…
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to…
Every day we are surrounded by spoken dialog. This medium delivers rich diverse streams of information auditorily; however, systematically understanding dialog can often be non-trivial. Despite the pervasiveness of spoken dialog, automated…
Punctuation restoration enhances the readability of text and is critical for post-processing tasks in Automatic Speech Recognition (ASR), especially for low-resource languages like Bangla. In this study, we explore the application of…
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…
We propose new, data-efficient training tasks for BERT models that improve performance of automatic speech recognition (ASR) systems on conversational speech. We include past conversational context and fine-tune BERT on transcript…
The incompleteness of speech inputs severely degrades the performance of all the related speech signal processing applications. Although many researches have been proposed to address this issue, they controlled the data missing conditions…
The fusion of speech and language in the era of large language models has garnered significant attention. Discrete speech token is often utilized in text-to-speech tasks for speech compression and portability, which is convenient for joint…
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…
Recent advances in Automatic Speech Recognition (ASR) have made it possible to reliably produce automatic transcripts of clinician-patient conversations. However, access to clinical datasets is heavily restricted due to patient privacy,…
Conversational speech often consists of deviations from the speech plan, producing disfluent utterances that affect downstream NLP tasks. Removing these disfluencies is necessary to create fluent and coherent speech. This paper presents…
Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…
Clinical diagnosis of stuttering requires an assessment by a licensed speech-language pathologist. However, this process is time-consuming and requires clinicians with training and experience in stuttering and fluency disorders.…
Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…