Effects of vocal effort and speaking style on text-independent speaker verification

Shriberg, Elizabeth; Graciarena, Martin; Bratt, Harry; Kathol, Andreas; Kajarekar, Sachin; Jameel, Huda Farooq; Richey, Colleen; Goodman, Fred

doi:10.21437/interspeech.2008-195

Cited by 31 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is in line with results showing that rich multi-modal information results in better representations of affective categories 48 . Similar evidence also exists from automatic voice recognition, demonstrating that training data from speakers under a variety of speech registers increases correct recognition probability of test data containing high variability 18 . This means that maximizing knowledge about within-voice variability supports the receivers' ability to identify a voice under a wide variety of registers and generalizes to previously unexperienced realizations of particular registers by a speaker.…”

Section: Discussionsupporting

confidence: 53%

“…Other than a mere shift between ADS and IDS -as argued by Piazza et al 4 -this means that the potential vocal space a speaker occupies is better represented in IDS compared to ADS registers, and further, that IDS includes the timbre space of ADS significantly more than the other way around. We thus obtained a rigorous acoustic model that explains the variability advantage demonstrated in prior studies in both computer 19 and human 38 voice recognition. This preprint research paper has not been peer reviewed.…”

Section: Acoustic Modelling: Ads Is a Timbre Subspace Of Idsmentioning

confidence: 99%

See 1 more Smart Citation

Mothers Reveal More of Their Vocal Identity When Talking to Infants

Kathiresan

Hervais-Adelman²,

Townsend³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

Section: Discussionsupporting

confidence: 53%

Section: Acoustic Modelling: Ads Is a Timbre Subspace Of Idsmentioning

confidence: 99%

Mothers Reveal More of Their Vocal Identity When Talking to Infants

Kathiresan

Hervais-Adelman²,

Townsend³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

“…As a result, such singer recognition systems can be less generalized to various singing styles and pronunciation effects. The voice of the a cappella solo singing is a speaking style that clearly demonstrates the singer's multiple features [9]. There are significant differences between the spoken language and a cappella solo of the same speaker.…”

mentioning

confidence: 97%

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Zhou

2023

IEEE Access

View full text Add to dashboard Cite

Singer recognition plays a vital role in music information retrieval systems. Most songs in the singer recognition system are mixed audios of music and voice. In contrast, there is a lack of labeled a cappella solo singing data suitable for singer recognition. Text-independent singer recognition systems successfully encode audio features such as voice pitch, intensity, and timbre to achieve good performance. Most such systems are trained and evaluated using data from music with accompaniment. However, due to the influence of background music, the performance of the singer recognition model was limited. Contrarily, a powerful singer identification system can be trained and evaluated using a cappella solo singing voices with a clear and broad range of qualities. There needs to be labeled clear singing data suitable for singer recognition research. To address this issue, we present Vocal92, a multivariate a cappella solo singing and speech audio dataset spanning around 146.73 hours sourced from volunteers. Furthermore, we use two current state-of-the-art models to construct the singer recognition baseline system. In experiments, the singer recognition model developed by a cappella solo singing data performs well in both single-mode and cross-modal verification data, significantly improving related works. The dataset is accessible to everyone at https://pan.baidu.com/s/1Pn62DHfal2OOZ_5JqgGBdQ with jnz5 as the validation code. For noncommercial use, the dataset will be available free of charge at the IEEE DataPort (after acceptance).

show abstract

Impact of Prior Channel Information for Speaker Identification

Vaquero

Scheffer

Karajekar

2009

Advances in Biometrics

View full text Add to dashboard Cite

Abstract. Joint factor analysis (JFA) has been very successful in speaker recognition but its success depends on the choice of development data. In this work, we apply JFA to a very diverse set of recording conditions and conversation modes in NIST 2008 SRE, showing that having channel matched development data will give improvements of about 50% in terms of Equal Error Rate against a Maximum a Posteriori (MAP) system, while not having it will not give significant improvement. To provide robustness to the system, we estimate eigenchannels in two ways. First, we estimate the eigenchannels separately for each condition and stack them. Second, we pool all the relevant development data and obtain a single estimate. Both techniques show good performance, but the former leads to lower performance when working with low-dimension channel subspaces, due to the correlation between those subspaces.

show abstract

Effects of vocal effort and speaking style on text-independent speaker verification

Cited by 31 publications

References 9 publications

Mothers Reveal More of Their Vocal Identity When Talking to Infants

Mothers Reveal More of Their Vocal Identity When Talking to Infants

Vocal92: Audio Dataset With a Cappella Solo Singing and Speech

Impact of Prior Channel Information for Speaker Identification

Contact Info

Product

Resources

About