VoiceMethods Creates Polish and Russian Speech Recognition System Development Tools
New York, NY - VoiceMethods LLC has begun licensing three new speech corpuses made especially for the development of speech recognition systems in Polish and Russian:
- Russian Acoustic-Phonetic Continuous Speech Corpus
- Polish Acoustic-Phonetic Continuous Speech Corpus
- Isolated Spoken Polish Alphabet Letters Corpus Around 250 speakers were recorded for these corpuses. All possible phonetic combinations occurring in natural speech were taken into account in the collection of spoken phrases; each sentence in the corpuses contains approximately 70 phonemes. The total running time of the three of the corpuses is close to 20 hours. Commenting on the development of speech corpuses, Anatoly Kissen, president of VoiceMethods, said, "We've created these corpuses not for academic purposes, but for the development of business solutions. Any developer of speaker-independent Polish and/or Russian speech recognition systems may acquire them to help achieve their goals. The corpuses may be used to create automated call centers, voice-operated e-mail access systems, voice dialing systems and more. I've noticed that the interest in speech recognition systems has increased as of late. Many of the obstacles in the development path, such as hardware limitations, have been surmounted. These are the real precursors of the impending boom in the development of the speech technologies market anticipated by leading analysts in Russia and the world."