SpeechPy - A Library for Speech Processing and Recognition

Torfi, Amirsina

doi:10.21105/joss.00749

Cited by 7 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…22.9% ± 0.84 85.6% ± 1.12 20 21.1% ± 0.73 87.3% ± 1.33 40 21.7% ± 0.82 86.1% ± 1.17 Table 2. The effect of the number of provided utterances on evaluation performance.…”

Section: Effect Of the Number Of Utterancesmentioning

confidence: 99%

See 1 more Smart Citation

Text-Independent Speaker Verification Using 3D Convolutional Neural Networks

Torfi

Dawson

Nasrabadi

2018

2018 IEEE International Conference on Multimedia and Expo (ICME)

Self Cite

View full text Add to dashboard Cite

In this paper, a novel method using 3D Convolutional Neural Network (3D-CNN) architecture has been proposed for speaker verification in the text-independent setting. One of the main challenges is the creation of the speaker models. Most of the previously-reported approaches create speaker models based on averaging the extracted features from utterances of the speaker, which is known as the d-vector system. In our paper, we propose an adaptive feature learning by utilizing the 3D-CNNs for direct speaker model creation in which, for both development and enrollment phases, an identical number of spoken utterances per speaker is fed to the network for representing the speakers' utterances and creation of the speaker model. This leads to simultaneously capturing the speaker-related information and building a more robust system to cope with within-speaker variation. We demonstrate that the proposed method significantly outperforms the traditional d-vector verification system. Moreover, the proposed system can also be an alternative to the traditional d-vector system which is a one-shot speaker modeling system by utilizing 3D-CNNs.

show abstract

“…22.9% ± 0.84 85.6% ± 1.12 20 21.1% ± 0.73 87.3% ± 1.33 40 21.7% ± 0.82 86.1% ± 1.17 Table 2. The effect of the number of provided utterances on evaluation performance.…”

Section: Effect Of the Number Of Utterancesmentioning

confidence: 99%

“…The extraction of MFECs is similar to MFCCs by discarding the DCT operation. SpeechPy package has been used for speech feature extraction [20].…”

Section: Data Representationmentioning

confidence: 99%

Text-Independent Speaker Verification Using 3D Convolutional Neural Networks

Torfi

Dawson

Nasrabadi

2018

2018 IEEE International Conference on Multimedia and Expo (ICME)

Self Cite

View full text Add to dashboard Cite

show abstract

“…For more general speech processing and filtering, SpeechPy is an open-source solution for "speech processing and feature extraction … [by providing the] most frequent used speech features including MFCCs and filterbank energies" (Torfi, 2018).…”

Section: Related Workmentioning

confidence: 99%

Speakerbox: Few-Shot Learning for Speaker Identification with Transformers

Brown¹,

Huynh²,

Weber³

2023

JOSS

View full text Add to dashboard Cite

Automated speaker identification is a modeling challenge for research when large-scale corpora, such as audio recordings or transcripts, are relied upon for evidence (e.g. Journalism, Qualitative Research, Law, etc.). To address current difficulties in training speaker identification models, we propose Speakerbox: a method for few-shot fine-tuning of an audio transformer. Specifically, Speakerbox makes multi-recording, multi-speaker identification model fine-tuning as simple as possible while still fitting an accurate, useful model for application. Speakerbox works by ensuring data are safely stratified by speaker id and held-out by recording id prior to fine-tuning of a pretrained speaker identification Transformer on a small number of audio examples. We show that with less than an hour of audio-recorded input, Speakerbox can fine-tune a multi-speaker identification model for use in assisting researchers in audio and transcript annotation.

show abstract