The Effect of Batch Size on Contrastive Self-Supervised Speech Representation Learning

1 code implementation • 21 Feb 2024 • Nik Vaessen, David A. van Leeuwen

We then show that the quality of the pre-trained model depends mainly on the amount of speech data seen during training, i. e., on the product of batch size and number of iterations.

Benchmarking Representation Learning +1

Speaker and Language Change Detection using Wav2vec2 and Whisper

no code implementations • 18 Feb 2023 • Tijn Berns, Nik Vaessen, David A. van Leeuwen

We investigate recent transformer networks pre-trained for automatic speech recognition for their ability to detect speaker and language changes in speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Training speaker recognition systems with limited data

1 code implementation • 28 Mar 2022 • Nik Vaessen, David A. van Leeuwen

These subsets are restricted to 50\, k audio files (versus over 1\, M files available), and vary on the axis of number of speakers and session variability.

Speaker Recognition

Fine-tuning wav2vec2 for speaker recognition

1 code implementation • 30 Sep 2021 • Nik Vaessen, David A. van Leeuwen

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition.

Classification Speaker Recognition +1

Large-Scale Speaker Diarization of Radio Broadcast Archives

no code implementations • 19 Jun 2019 • Emre Yilmaz, Adem Derinel, Zhou Kun, Henk van den Heuvel, Niko Brummer, Haizhou Li, David A. van Leeuwen

This paper describes our initial efforts to build a large-scale speaker diarization (SD) and identification system on a recently digitized radio broadcast archive from the Netherlands which has more than 6500 audio tapes with 3000 hours of Frisian-Dutch speech recorded between 1950-2016.

speaker-diarization Speaker Diarization +1

Semi-supervised acoustic model training for speech with code-switching

no code implementations • 23 Oct 2018 • Emre Yilmaz, Mitchell McLaren, Henk van den Heuvel, David A. van Leeuwen

In this paper, we describe several automatic annotation approaches to enable using of a large amount of raw bilingual broadcast data for acoustic model training in a semi-supervised setting.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Acoustic and Textual Data Augmentation for Improved ASR of Code-Switching Speech

no code implementations • 28 Jul 2018 • Emre Yilmaz, Henk van den Heuvel, David A. van Leeuwen

In this paper, we describe several techniques for improving the acoustic and language model of an automatic speech recognition (ASR) system operating on code-switching (CS) speech.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Calibration of Phone Likelihoods in Automatic Speech Recognition

no code implementations • 14 Jun 2016 • David A. van Leeuwen, Joost van Doremalen

In this paper we study the probabilistic properties of the posteriors in a speech recognition system that uses a deep neural network (DNN) for acoustic modeling.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

The "Sprekend Nederland" project and its application to accent location

no code implementations • 8 Feb 2016 • David A. van Leeuwen, Rosemary Orr

This paper describes the data collection effort that is part of the project Sprekend Nederland (The Netherlands Talking), and discusses its potential use in Automatic Accent Location.

Constrained speaker linking

no code implementations • 26 Mar 2014 • David A. van Leeuwen, Niko Brümmer

In this paper we study speaker linking (a. k. a.\ partitioning) given constraints of the distribution of speaker identities over speech recordings.

Speaker Recognition