Results 91 to 100 of about 231,551 (186)

Unsupervised adaptation of PLDA models for broadcast diarization

EURASIP Journal on Audio, Speech, and Music Processing, 2019
We present a novel model adaptation approach to deal with data variability for speaker diarization in a broadcast environment. Expensive human annotated data can be used to mitigate the domain mismatch by means of supervised model adaptation approaches ...
Ignacio Viñals, Alfonso Ortega, Jesús Villalba, Antonio Miguel, Eduardo Lleida   +4 more
doaj   +1 more source

Speaker Diarization with Deep Learning Techniques

, 2020
Speaker diarization is a task to identify the speaker when different speakers spoke in an audio or video recording environment. Artificial intelligence (AI) fields have effectively used Deep Learning (DL) to solve a variety of real-world application ...
Kshirod, Kshirod Sarmah
core   +1 more source

Relative Applicability of Diverse Automatic Speech Recognition Platforms for Transcription of Psychiatric Treatment Sessions

IEEE Access
Service delivery in mental healthcare involves documentation of sensitive patient-clinician conversations that require serious caution. Conventionally, clinicians take handwritten notes, which causes low readability and lack of database which hinders ...
Rana Zeeshan, John Bogue, Mamoona Naveed Asghar   +2 more
doaj   +1 more source

Towards measuring and scoring speaker diarization fairness

Speaker diarization, or the task of finding "who spoke and when", is now used in almost every speech processing application. Nevertheless, its fairness has not yet been evaluated because there was no protocol to study its biases one by one. In this paper
Petitpont, Frédéric, Boudy, Jérôme, Tevissen, Yannis, Chollet, Gérard   +3 more
core   +1 more source

Active Speaker Detection Using Audio, Visual, and Depth Modalities: A Survey

IEEE Access
The rapid progress of multimodal signal processing in recent years has cleared the way for novel applications in human-computer interaction, surveillance, and telecommunication.
Siti Nur Aisyah Mohd Robi, Muhammad Atiff Zakwan Mohd Ariffin, Mohd Azri Mohd Izhar, Norulhusna Ahmad, Hazilah Mad Kaidi   +4 more
doaj   +1 more source

Improving speaker diarization for naturalistic child-adult conversational interactions using contextual information. [PDF]

J Acoust Soc Am, 2020
Kumar M, Kim SH, Lord C, Narayanan S.
europepmc   +1 more source

Echo: A crowd-sourced Romanian speech dataset.

Interaction Design and Architecture(s)
Romanian is the seventh most popular European language, with around 30 million speakers worldwide. Despite its popularity, the available speech resources are limited.
Remus-Dan Ungureanu, Mihai Dascalu
doaj   +1 more source

A Unified Pipeline for Low-Resource Speech Recognition and Understanding: Low-Rank Adaptation, Speaker Diarization, and Graph-Based Retrieval-Augmented Generation

Applied Sciences
Macedonian is a low-resource language for automatic speech recognition: annotated speech data are scarce, dialectal variation is substantial, and existing evaluations focus almost entirely on read speech in Standard Macedonian.
Marija Stojcheva, Goran Petkovski, Igor Mishkovski   +2 more
doaj   +1 more source

Speaker Diarization from Bangla Conversation

pdf fileSpeaker diarization is a fundamental task in speech processing that aims to identify and segment different speakers within an audio recording. It involves determining ”who spoke when” in a given conversation or speech.
Chowdhury, Kibtia
core  

Diart: A Python Library for Real-Time Speaker Diarization

International audienceThe term "speaker diarization" denotes the problem of determining "who speaks when" in a recorded conversation. Among other reasons, it has attracted the attention of the speech research community because of its ability to improve ...
Higy, Bertrand, Bredin, Hervé, Fruend, Ingo, Coria, Juan Manuel, Ghannay, Sahar, Kesari, Amit, Zaouk, Khaled, Rosset, Sophie, Thakkar, Yagna   +8 more
core   +1 more source