ALIZE, a free toolkit for speaker recognition

Bonastre, Jean-François; Wils, F.; Meignier, Sylvain

doi:10.1109/icassp.2005.1415219

Cited by 123 publications

(63 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Current techniques and toolkits (for example, ALIZE [57]) will provide a firm base to start from, but new methods, particularly combining information from many different approaches (as is currently done in the speaker recognition field [58]) will need to be developed to allow diarization to be maximally beneficial to real users and potential downstream processing such as machine translation and parsing. Additionally, further development of tools to allow user interactions with diarization output for specific jobs will help focus the research to contribute to high-utility human language technology.…”

Section: Discussionmentioning

confidence: 99%

An overview of automatic speaker diarization systems

Tranter

Reynolds

2006

IEEE Trans. Audio Speech Lang. Process.

507

300

View full text Add to dashboard Cite

Abstract-Audio diarization is the process of annotating an input audio channel with information that attributes (possibly overlapping) temporal regions of signal energy to their specific sources. These sources can include particular speakers, music, background noise sources, and other signal source/channel characteristics. Diarization can be used for helping speech recognition, facilitating the searching and indexing of audio archives, and increasing the richness of automatic transcriptions, making them more readable. In this paper, we provide an overview of the approaches currently used in a key area of audio diarization, namely speaker diarization, and discuss their relative merits and limitations. Performances using the different techniques are compared within the framework of the speaker diarization task in the DARPA EARS Rich Transcription evaluations. We also look at how the techniques are being introduced into real broadcast news systems and their portability to other domains and tasks such as meetings and speaker verification.

show abstract

Section: Discussionmentioning

confidence: 99%

An overview of automatic speaker diarization systems

Tranter

Reynolds

2006

IEEE Trans. Audio Speech Lang. Process.

507

300

View full text Add to dashboard Cite

show abstract

“…Mô hình hỗn hợp Gauss đa thể hiện (Gaussian Mixture Model: GMM) đã được sử dụng trong các nghiên cứu về nhận dạng người nói [3], định danh phương ngữ tiếng Anh [4], tiếng Trung [5], tiếng Thái [6], tiếng Hindi [7], tiếng Việt [8], nhận dạng ngôn ngữ [9], [10]. Supervectors cũng được sử dụng trong nghiên cứu nhận dạng phương ngữ và cho kết quả khả quan [11].…”

Section: B Nhận Dạng Phương Ngữ Tiếng Việt Dùng Mô Hình Gmm Với Mfccunclassified

Cải Thiện Hiệu Năng Hệ Thống Nhận Dạng Tiếng Việt Với Thông Tin Về Phương Ngữ

Hùng¹,

Loan²,

Quang³

et al. 2017

Fair - Nghiên Cứu Cơ Bản Và Ứng Dụng Công Nghệ Thông Tin - 2016

View full text Add to dashboard Cite

“…Also described here is our approach to speaker purification and system combination. Both bottom-up and top-down speaker diarization systems were implemented with the ALIZE toolkit [25], which ensures that the comparative study better reflects core differences in the clustering and segmentation strategies instead of any nuances related to differences in estimation, decoding, or adaptation algorithms.…”

Section: Experimental Systemsmentioning

confidence: 99%

A Comparative Study of Bottom-Up and Top-Down Approaches to Speaker Diarization

Evans

Bozonnet

Wang

et al. 2012

IEEE Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-This paper presents a theoretical framework to analyze the relative merits of the two most general, dominant approaches to speaker diarization involving bottom-up and top-down hierarchical clustering. We present an original qualitative comparison which argues how the two approaches are likely to exhibit different behavior in speaker inventory optimization and model training: bottom-up approaches will capture comparatively purer models and will thus be more sensitive to nuisance variation such as that related to the speech content; top-down approaches, in contrast, will produce less discriminative speaker models but, importantly, models which are potentially better normalized against nuisance variation. We report experiments conducted on two standard, single-channel NIST RT evaluation datasets which validate our hypotheses. Results show that competitive performance can be achieved with both bottom-up and top-down approaches (average DERs of 21% and 22%), and that neither approach is superior. Speaker purification, which aims to improve speaker discrimination, gives more consistent improvements with the top-down system than with the bottom-up system (average DERs of 19% and 25%), thereby confirming that the top-down system is less discriminative and that the bottom-up system is less stable. Finally, we report a new combination strategy that exploits the merits of the two approaches. Combination delivers an average DER of 17% and confirms the intrinsic complementary of the two approaches.

show abstract

ALIZE, a free toolkit for speaker recognition

Cited by 123 publications

References 3 publications

An overview of automatic speaker diarization systems

An overview of automatic speaker diarization systems

Cải Thiện Hiệu Năng Hệ Thống Nhận Dạng Tiếng Việt Với Thông Tin Về Phương Ngữ

A Comparative Study of Bottom-Up and Top-Down Approaches to Speaker Diarization

Contact Info

Product

Resources

About