Far-Field Speaker Recognition Benchmark Derived From The DiPCo Corpus (2022.lrec-1)
Copied to clipboard
| Challenge: | Using a publicly-available corpus, we propose a far-field speaker verification benchmark. |
| Approach: | They propose a far-field speaker verification benchmark derived from the publicly available DiPCo corpus. |
| Outcome: | The proposed tasks are very challenging and hope to inspire the speech community to develop new methods and systems for this challenging domain. |
Similar Papers
RoboVox: A Single/Multi-channel Far-field Speaker Recognition Benchmark for a Mobile Robot (2024.lrec-main)
Copied to clipboard
Mohammad Mohammadamini, Driss Matrouf, Michael Rouvier, Jean-Francois Bonastre, Romain Serizel, Theophile Gonos
| Challenge: | In this paper, we introduce a new far-field speaker recognition benchmark called RoboVox. |
| Approach: | They introduce a new far-field speaker recognition benchmark called RoboVox which measures the far-feet of a French corpus recorded by a mobile robot. |
| Outcome: | The proposed benchmarks show a significant decline in far-field speaker recognition and urge the community to further research in this domain. |
ALLIES: A Speech Corpus for Segmentation, Speaker Diarization, Speech Recognition and Speaker Change Detection (2024.lrec-main)
Copied to clipboard
| Challenge: | a meta corpus of audio files is used to gather, annotate and transcribe speech . a large number of speech databases are needed to perform multi-speaker tasks such as speaker diarization and speaker change detection. |
| Approach: | They propose to use human feedback to homogenize and correct speaker labels among the audio files by integrating human feedback within a speaker verification system. |
| Outcome: | The proposed protocol evaluates speech segmentation, speaker diarization, speech transcription and speaker change detection using human feedback. |
FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification Systems (2022.findings-naacl)
Copied to clipboard
| Challenge: | Linguistic bias in Deep Neural Network (DNN) based systems is a critical challenge that needs attention. |
| Approach: | They propose to integrate a lightweight embedding with existing NLP systems to mitigate linguistic bias without adaptation. |
| Outcome: | The proposed framework reduces linguistic bias and enhances usability of baselines for twelve languages. |
SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditions (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks only evaluate a subset of potential conditions, missing others entirely. |
| Approach: | a new benchmark suite evaluates speaker verification models under a variety of stressors . a san francisco-based team evaluates models under natural and background conditions . |
| Outcome: | a new benchmark suite evaluates speaker verification models under stressors under a variety of conditions . the results show that some models perform better under stress conditions than others . |
MirasVoice: A bilingual (English-Persian) speech corpus (L18-1)
Copied to clipboard
| Challenge: | Existing research and development areas in speech recognition are focused on the language of speakers. |
| Approach: | They propose to use a bilingual (English-Farsi) speech corpus to validate and explore speaker verification systems. |
| Outcome: | The proposed corpus can be used in a variety of language dependent and independent applications. |
Computer-assisted Speaker Diarization: How to Evaluate Human Corrections (L18-1)
Copied to clipboard
| Challenge: | a framework to evaluate the human corrections of a speaker diarization is presented for the French National Audiovisual Institute (INA) the speaker diaarization task is a necessary pre-processing step for speaker identification and speech transcription. |
| Approach: | They propose a framework to evaluate the human corrections of a speaker diarization . they propose four elementary actions to correct the diarized speaker and an automaton to simulate the correction sequence. |
| Outcome: | The proposed framework copes with the needs of the French National Audiovisual Institute (INA) due to the increasing number of documents and the limited number of annotators, many documents remain undocumented or only partly documented. |
Speaker Verification in Agent-generated Conversations (2024.acl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have increased the capabilities of conversational AI to solve challenging dialogue problems. |
| Approach: | They propose a task to verify whether two sets of utterances originate from the same speaker. |
| Outcome: | The proposed task aims to verify whether two sets of utterances originate from the same speaker. |
PRiSM: Benchmarking Phone Realization in Speech Models (2026.acl-long)
Copied to clipboard
Shikhar Bharadwaj, Chin-Jou Li, Yoonjae Kim, Kwanghee Choi, Eunjung Yeo, Ryan Soh-Eun Shim, Hanyu Zhou, Brendon Boldt, Karen Rosero, Kalvin Chang, Darsh Agrawal, Keer Xu, Chao-Han Huck Yang, Jian Zhu, Shinji Watanabe, David R. Mortensen
| Challenge: | Existing evaluations of phone recognition systems only measure surface-level transcription accuracy. |
| Approach: | They propose to standardize transcription-based evaluation and assess downstream utility in clinical, educational, and multilingual settings with transcription and representation probes. |
| Outcome: | The proposed system outperforms LALMs in clinical, educational, and multilingual settings. |
Common Voice: A Massively-Multilingual Speech Corpus (2020.lrec-1)
Copied to clipboard
Rosana Ardila, Megan Branson, Kelly Davis, Michael Kohler, Josh Meyer, Michael Henretty, Reuben Morais, Lindsay Saunders, Francis Tyers, Gregor Weber
| Challenge: | Common Voice is a massively-multilingual collection of transcribed speech intended for speech technology research and development. |
| Approach: | They propose to use Mozilla’s DeepSpeech Speech-to-Text toolkit to perform multilingual automatic speech recognition experiments. |
| Outcome: | The proposed corpus is the largest in the public domain for speech recognition, both in terms of hours and languages. |
A Crowdsourced Open-Source Kazakh Speech Corpus and Initial Speech Recognition Baseline (2021.eacl-main)
Copied to clipboard
Yerbolat Khassanov, Saida Mussakhojayeva, Almas Mirzakhmetov, Alen Adiyev, Mukhamet Nurpeiissov, Huseyin Atakan Varol
| Challenge: | The Kazakh speech corpus contains over 153,000 utterances spoken by participants from different regions and age groups, as well as both genders. |
| Approach: | They propose to build an open-source Kazakh speech corpus for the Kazakh language that contains over 153,000 transcribed audio . they describe the data collection and preprocessing procedures followed by a description of the database specifications. |
| Outcome: | The Kazakh speech corpus contains over 153,000 utterances spoken by participants from different regions and age groups, as well as both genders. |