Related papers: Can Authorship Attribution Models Distinguish Spea…

Speech-to-speech translation combines machine translation with speech synthesis, introducing evaluation challenges not present in either task alone. How to automatically evaluate speech-to-speech translation is an open question which has…

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Large language models (LLMs) have shown impressive results while requiring little or no direct supervision. Further, there is mounting evidence that LLMs may have potential in information-seeking scenarios. We believe the ability of an LLM…

The media localization industry usually requires a verbatim script of the final film or TV production in order to create subtitles or dubbing scripts in a foreign language. In particular, the verbatim script (i.e. as-broadcast script) must…

In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i.e. human transcriptions, instead of Automatic Speech Recognition (ASR)'s…

In the current Large Language Model (LLM) ecosystem, creators have little agency over how their data is used, and LLM users may find themselves unknowingly plagiarizing existing sources. Attribution of LLM-generated text to LLM input data…

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…

The development of privacy-preserving automatic speaker verification systems has been the focus of a number of studies with the intent of allowing users to authenticate themselves without risking the privacy of their voice. However, current…

The emergence of human-like abilities of AI systems for content generation in domains such as text, audio, and vision has prompted the development of classifiers to determine whether content originated from a human or a machine. Implicit in…

A method for authorship attribution based on function word adjacency networks (WANs) is introduced. Function words are parts of speech that express grammatical relationships between other words but do not carry lexical meaning on their own.…

Speaker verification is to judge the similarity between two unknown voices in an open set, where the ideal speaker embedding should be able to condense discriminant information into a compact utterance-level representation that has small…

Researchers have demonstrated that Automatic Speech Recognition (ASR) systems perform differently across demographic groups. In this work, we examined how subtitle errors affect evaluations of speakers and their content using a…

The Streaming Unmixing and Recognition Transducer (SURT) has recently become a popular framework for continuous, streaming, multi-talker speech recognition (ASR). With advances in architecture, objectives, and mixture simulation methods, it…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Large language models (LLMs) such as GPT-4, PaLM, and Llama have significantly propelled the generation of AI-crafted text. With rising concerns about their potential misuse, there is a pressing need for AI-generated-text forensics. Neural…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

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…

Direct speech-to-speech translation (S2ST) with discrete self-supervised representations has achieved remarkable accuracy, but is unable to preserve the speaker timbre of the source speech. Meanwhile, the scarcity of high-quality…

The performance of speaker verification degrades significantly when the test speech is corrupted by interference speakers. Speaker diarization does well to separate speakers if the speakers are temporally overlapped. However, if…

Interpretability is an important area of research for safe deployment of machine learning systems. One particular type of interpretability method attributes model decisions to input features. Despite active development, quantitative…