🧑‍🔬 George Saon

🏛️ Affiliations

🏢IBMArmonk · United States2000–2026 · 93 paperscurrent🔬IBM Research - Thomas J. Watson Research CenterYorktown Heights · United States2000–2025 · 71 papers🔬Laboratoire Lorrain de Recherche en Informatique et ses ApplicationsNancy · France1997–2002 · 6 papers🔬Centre National de la Recherche ScientifiqueParis · France1997–2002 · 4 papers🤝READ GlobalSan Francisco · United States1994–1998 · 2 papers

🏛️IBMYorktown Heights · United States1998Employment since 1998 · Distinguished Research Scientist, Research

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

🧭 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. English Conversational Telephone Speech Recognition by Humans and Machines (2017 · 382 citations)
   The paper tests the claim that machines reached human-level accuracy on conversational telephone speech. It also reports a stronger IBM recognizer. The authors hired the transcription vendor Appen to run their own human benchmark on the Switchboard (SWB) and CallHome (CH) subsets of the NIST Hub5 2000 test set. Three…
2. Direct Acoustics-to-Word Models for English Conversational Speech Recognition (2017 · 121 citations)
   The paper asks whether one neural network can turn speech directly into words, with no phone inventory, pronunciation dictionary, language model or decoder.
3. Building competitive direct acoustics-to-word models for English conversational speech recognition (2017 · 111 citations)
   Direct acoustics-to-word (A2W) models map speech straight to whole words with one neural network. They need no pronunciation lexicon, no decoder and no separately trained language model. Earlier work suggested such models need vastly more audio than phone- or character-based systems, and the authors' own previous A2W…
4. The IBM 2015 English Conversational Telephone Speech Recognition System (2015 · 96 citations)
   The paper reports how IBM improved its English recognizer for conversational telephone speech. The benchmark is the Switchboard part of the Hub5-2000 evaluation. Training used 1975 hours of two-party phone conversations from Switchboard 1, Fisher and CallHome. The authors argue that no single trick is enough and that…
5. On the limit of English conversational speech recognition (2021 · 49 citations)
   The paper asks how much further attention-based encoder-decoder ASR can be pushed on the Switchboard conversational telephone benchmark. The authors start from their earlier heavily regularized single-head LSTM encoder-decoder system. They then add several improvements:
6. English Broadcast News Speech Recognition by Humans and Machines (2019 · 12 citations)
   The paper asks whether deep-learning recipes that brought conversational telephone speech (CTS) recognition near human level also work for English broadcast news (BN).
7. The IBM 2016 English Conversational Telephone Speech Recognition System (2016 · 3 citations)
   The paper reports how IBM pushed English conversational telephone speech recognition to a record word error rate of 6.6% on the Switchboard portion of the Hub5 2000 evaluation.

🤝 Co-authors here

10 co-authors with a page, the most papers together first.

• Michael Picheny ×5
• Bhuvana Ramabhadran ×3
• Brian Kingsbury ×3
• Kartik Audhkhasi ×3
• Gakuto Kurata ×2
• Hong-Kwang J. Kuo ×2
• Samuel Thomas ×2
• Steven Rennie ×2
• Tom Sercu ×2
• Zoltan Tuske ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Interspeech ×4: Interspeech 2021, Interspeech 2017 ×2, Interspeech 2015
• IEEE International Conference on Acoustics Speech and Signal Processing ×2: IEEE International Conference on Acoustics Speech and Signal Processing 2019, IEEE International Conference on Acoustics Speech and Signal Processing 2017

🔗 Cited by

Papers of our library cite their works 70 times (of the 141,840 papers whose bibliographies we read); 12 citing papers with a page here →.

Updated 24 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/george-saon/