VOICE PROCESSING UNIT AND VOICE PROCESSING METHOD

• Main Author: MIYAMOTO MASANARI
• Format: Patent
• Language: English; Japanese
• Published: 13.09.2021
• Subjects: ACOUSTICS; MUSICAL INSTRUMENTS; PHYSICS; SPEECH ANALYSIS OR SYNTHESIS; SPEECH OR AUDIO CODING OR DECODING; SPEECH OR VOICE PROCESSING; SPEECH RECOGNITION

To adaptively suppress, even when any speaker in a plurality of speakers present in a closed space utters, acoustic crosstalk components caused by utterance voices of other speakers that can be mixed in the utterance voice of the speaker, and to improve the sound quality of the utterance voice.SOLUTION: An acoustic crosstalk suppression device detects a single talk state in which any one of a plurality of persons is uttering on the basis of the voice signals collected by a plurality of microphones, estimates a first mixing ratio and a second mixing ratio on the basis of the sound pressure ratio of the voice signal collected in the single talk state of a first speaker who is an arbitrary speaker and the sound pressure ratio of the voice signal collected in a single talk of a second speaker, and determines which one of a first crosstalk component due to the utterance of the second speaker mixed in the voice signal of the first speaker and a second crosstalk component due to the utterance of the first speaker mixed in the voice signal of the second speaker should be suppressed.SELECTED DRAWING: Figure 3 【課題】閉空間に存在する複数の話者のうちいずれの話者が発話した場合でも、その話者の発話音声に含まれ得る他の話者の発話音声による音響的なクロストーク成分を適応的に抑圧し、発話音声の音質を改善する。【解決手段】音響クロストーク抑圧装置は、複数のマイクにより収音された音声信号に基づいて、複数人のうちいずれか一人が発話しているシングルトーク状態を検出し、任意の話者である第１の話者のシングルトーク状態で収音された音声信号の音圧比率と、第２の話者のシングルトーク状態で収音された音声信号の音圧比率とに基づいて、第１の混合率および第２の混合率を推定し、第１の話者の音声信号に含まれる第２の話者の発話による第１のクロストーク成分、および、第２の話者の音声信号に含まれる第１の話者の発話による第２のクロストーク成分のうちいずれの抑圧を行うかを判別する。【選択図】図３