Interspeech: Interspeech (combined EuroSpeech and ICSLP in 2000) — papers and institutions, 2024–2026

Papers of Interspeech, Interspeech (combined EuroSpeech and ICSLP in 2000) (CORE rank A; field: Artificial intelligence), 2024–2026: per year, the institutions, countries and topics, and the most-cited papers. Ranks are those of the CORE Conference Rankings, edition ICORE2026 (portal.core.edu.au), applied to every year shown. Papers are the works OpenAlex lists for the conference's proceedings, or for the issues of a conference-linked journal that publishes its papers (such as PACMPL, PVLDB or ACM TOG), by publication year; workshops, companion volumes, posters and Findings are left out. A paper counts once for each institution and country among its authors' affiliations as OpenAlex assigns them; papers without affiliations in OpenAlex count for none. For conferences published in book series that OpenAlex files as one source (LNCS, LIPIcs, SIAM and IOS Press proceedings), the papers are found by DOI: those of the volumes with the conference's title in Crossref, or LIPIcs DOIs, which name the conference. Conferences without DOIs (PMLR, USENIX, OpenReview) are listed without counts. A dash (–) for a year means OpenAlex has no papers of the conference for it yet: the proceedings are not published or indexed yet, or the conference did not meet that year (some meet every other year). 2026 counts what OpenAlex had indexed by 2026-11-02. Also as Markdown.

← All conferences

Key findings#

Interspeech (Interspeech (combined EuroSpeech and ICSLP in 2000)) is rated A by the CORE Conference Rankings (ICORE2026); OpenAlex lists 2,177 of its papers from 2024–2026 (1,026 in 2024, 1,151 in 2025; 2026 not in OpenAlex yet).
By the countries of the authors' institutions, the most papers come from France (56), the United States (27) and China (19).
The institutions with the most papers are Centre National de la Recherche Scientifique (10), Aix-Marseille Université (8) and Le Mans Université (6).
Its most-cited paper of these years is “XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model” (2024), with 129 citations.
OpenAlex has affiliations for only 7% of its papers, so the institution and country counts are incomplete.

Papers per year#

Interspeech papers per publication year in OpenAlex (–: not in OpenAlex yet)
Year	Papers	With affiliations
2024	1,026	114
2025	1,151	31
2026	–	–

Sources#

Where OpenAlex lists the papers
OpenAlex source	Which papers
S4393918409	The conference's proceedings

Who publishes there#

Institutions with the most Interspeech papers, 2024–2026
#	Institution	Papers
1	Centre National de la Recherche Scientifique	10
2	Aix-Marseille Université	8
3	Le Mans Université	6
4	Laboratoire Parole et Langage	6
5	Laboratoire Interdisciplinaire des Sciences du Numérique	6
6	Laboratoire d’Informatique de l’Université du Mans	6
7	Institut de Recherche en Informatique de Toulouse	5
8	Laboratoire Informatique d'Avignon	5
9	GIPSA-Lab	5
10	National University of Singapore	4

Countries with the most Interspeech papers, 2024–2026
#	Country	Papers
1	France	56
2	United States	27
3	China	19
4	Germany	9
5	South Korea	9
6	Denmark	7
7	United Kingdom	6
8	Japan	6
9	Australia	5
10	Switzerland	5

Keywords with the most Interspeech papers, 2024–2026
#	Keyword	Papers
1	speech recognition	334
2	speech synthesis	173
3	speech enhancement	135
4	large language models	115
5	text-to-speech	103
6	speech emotion recognition	88
7	low-resource languages	84
8	self-supervised learning	66
9	speaker verification	65
10	prosody	64

Most-cited papers#

Most-cited Interspeech papers of 2024–2026 (citations counted by OpenAlex)
#	Citations	Title	Published	Authors
1	129	XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model	2024-09-01	Edresson Casanova, Kelly Davis, Eren Gölge et al.
2	52	EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberation	2024-09-01	Julius Richter, Yi-Chiao Wu, Steven Krenn et al.
3	41	OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer	2024-09-01	Yifan Peng, Jinchuan Tian, William Chen et al.
4	41	Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection	2024-09-01	Duc-Tuan Truong, Ruijie Tao, Tuan Lam Nguyen et al.
5	35	EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark	2024-09-01	Ziyang Ma, Mingjie Chen, Hezhao Zhang et al.
6	35	LoRA-Whisper: Parameter-Efficient and Extensible Multilingual ASR	2024-09-01	Zheshu Song, Jianheng Zhuo, Yifan Yang et al.
7	34	Less is More: Accurate Speech Recognition & Translation without Web-Scale Data	2024-09-01	Krishna C. Puvvada, Piotr Żelasko, He Huang et al.
8	32	RawBMamba: End-to-End Bidirectional State Space Model for Audio Deepfake Detection	2024-09-01	Yujie Chen, Jiangyan Yi, Jun Xue et al.
9	32	Attentive Merging of Hidden Embeddings from Pre-trained Speech Model for Anti-spoofing Detection	2024-09-01	Zihan Pan, Tianchi Liu, Hardik B. Sailor et al.
10	31	URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement	2024-09-01	Wangyou Zhang, Robin Scheibler, Kohei Saijo et al.

Conferences in the same field#

AAAI · EMNLP · ACL · ICRA · IJCAI · HRI · EC · KR · ICAPS · IROS · NAACL · AAMAS · CIKM · ECAI · EACL · GECCO · IJCAR · CP · SAT · CADE · FOGA

Cite this page

Scholar4AI. (2026). Interspeech: Interspeech (combined EuroSpeech and ICSLP in 2000) — papers and institutions, 2024–2026. Journal and Conference Research Rankings. Retrieved November 2, 2026, from https://scholar4ai.com/proceedings/interspeech

@misc{scholar4ai-proceedings-interspeech,
  author = {{Scholar4AI}},
  title = {Interspeech: Interspeech (combined EuroSpeech and ICSLP in 2000) — papers and institutions, 2024–2026},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/proceedings/interspeech}},
  urldate = {2026-11-02},
  note = {Journal and Conference Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}

Free to reuse for non-commercial purposes with attribution (CC BY-NC 4.0).