API Build-data JSON Resources
Theme

Choose how MSRBot.io looks on this device.

Auto (match system) Light mode Dark mode

Preference is stored in this browser only.

SMPTE Meetings and Conferences ( November 2020)
[ACTIVE]

“AI News Anchor” with Deep Learning-based Speech Synthesis

Metadata

Publisher
SMPTE — White Plains, NY, USA
Doc Type
Conference Paper
Content Type
Original Research
Volume
2020, No. 11, pp. 1–13
Abstract
Deep learning-based text-to-speech (DL-TTS) is used in various situations and the sound quality is close to that of humans. We previously developed a news-specific DL-TTS system and implemented it to our AI news anchor for live broadcast programs and automatic news-speech distribution services. — We also developed our DL-TTS system for controlling speaking style and speech speed, pitch, intonation, and volume to facilitate the creation of various programs. More specifically, this method enables the changing of specific speaking styles, such as news style that mimics the style of news reporters, and conversation style. The purpose of creating this system was to eliminate discomfort due to differences in speech and speaking styles. Controlling the speaking-style is important in news speech because a mismatched speaking style does not appropriately convey news articles. For this study, we conducted an evaluation experiment on the conveying of simple news articles for language learners regarding speaking-style control and found appropriate speaking styles for automatically generated news speech. We conducted another evaluation experiment on whether synthetic speech generated from our system for “easy news” for Japanese language learners is useful for helping people understand the news in Japanese. We also discuss practical applications of our system. — Our news-specific deep neural network based-TTS system was found to effectively provide new services to broadcast stations. In the future, we will consider various use cases of flexible production by using a cloud system. The coronavirus pandemic has forced broadcasters to adopt new working styles. Thus, we will explore a new production system, such as a cloud-based system, for newsspeech automation for this new normal.
Publication Date
2020-11-10
DOI
10.5594/M001915
Link
https://doi.org/10.5594/M001915
Author(s)
Kiyoshi KuriharaNHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, 1-10-11 Kinuta, Setagaya, Tokyo 157-8510, Japan
Nobumasa SeiyamaNHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, 1-10-11 Kinuta, Setagaya, Tokyo 157-8510, Japan
Tadashi KumanoNHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories, 1-10-11 Kinuta, Setagaya, Tokyo 157-8510, Japan
Takashi FukayaNHK (Japan Broadcasting Corporation), 2-2-1 Jinnan, Shibuya, Tokyo 150-8001, Japan
Kazunari SaitoNHK (Japan Broadcasting Corporation), 2-2-1 Jinnan, Shibuya, Tokyo 150-8001, Japan
Satoshi SuzukiNHK (Japan Broadcasting Corporation), 2-2-1 Jinnan, Shibuya, Tokyo 150-8001, Japan
Keyword(s)
Text-to-Speech, AI News Anchor, Automatic Generated News Speech
Copyright
© 2020 Society of Motion Picture and Television Engineers, Inc.

Bibliographic Reference(s)

Source Data (JSON)

Full registry record with provenance metadata. Open directly: /api/doc/10.5594-M001915.json

Reference Tree

Explore all references and references to this document, as a navigable tree.

Open Reference Tree
Reference this Doc

Plain text (ISO 690 compliant)

Preview:
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; “AI News Anchor” with Deep Learning-based Speech Synthesis, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020. Available at https://doi.org/10.5594/M001915
Snippet:
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; “AI News Anchor” with Deep Learning-based Speech Synthesis, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020. Available at https://doi.org/10.5594/M001915

HTML (ISO 690 compliant)

Preview:
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; “AI News Anchor” with Deep Learning-based Speech Synthesis, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020. Available at https://doi.org/10.5594/M001915
Snippet:
<span class="citation">Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; <cite>“AI News Anchor” with Deep Learning-based Speech Synthesis</cite>, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020. Available at <a href="https://doi.org/10.5594/M001915" target="_blank" rel="noopener">https://doi.org/10.5594/M001915</a></span>

SMPTE Icon SMPTE's HTML Pub

Preview:
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; “AI News Anchor” with Deep Learning-based Speech Synthesis, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020
doi: 10.5594/M001915
url: https://doi.org/10.5594/M001915
Snippet:
<li>
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Takashi Fukaya, Kazunari Saito, and Satoshi Suzuki; <cite id="bib-10-5594-m001915">“AI News Anchor” with Deep Learning-based Speech Synthesis</cite>, SMPTE Meetings and Conferences ( November 2020); SMPTE, 2020
<span class="doi">10.5594/M001915</span>
</li>