Department of Machine Intelligence, Peking University, Beijing, China.
Department of Speech and Hearing Sciences, Indiana University Bloomington, 200 South Jordan Avenue, Bloomington, Indiana 47405, USA.
J Acoust Soc Am. 2019 Jul;146(1):445. doi: 10.1121/1.5116691.
Speech material influences the relative contributions of different frequency regions to intelligibility for English. In the current study, whether a similar effect of speech material is present for Mandarin Chinese was investigated. Speech recognition was measured using three speech materials in Mandarin, including disyllabic words, nonsense sentences, and meaningful sentences. These materials differed from one another in terms of the amount of contextual information and word frequency. The band importance function (BIF), as defined under the Speech Intelligibility Index (SII) framework, was used to quantify the contributions across frequency regions. The BIFs for the three speech materials were estimated from 16 adults who were native speakers of Mandarin. A Bayesian adaptive procedure was used to efficiently estimate the octave-frequency BIFs for the three materials for each listener. As the amount of contextual information increased, low-frequency bands (e.g., 250 and 500 Hz) became more important for speech recognition, consistent with English. The BIF was flatter for Mandarin than for comparable English speech materials. Introducing the language- and material-specific BIFs to the SII model led to improved predictions of Mandarin speech-recognition performance. Results suggested the necessity of developing material-specific BIFs for Mandarin.
语音材料会影响不同频率区域对英语可理解度的相对贡献。在本研究中,研究了语音材料对汉语普通话是否存在类似的影响。使用三种汉语普通话语音材料(双音节词、无意义句子和有意义句子)来测量语音识别。这些材料在语境信息量和词频方面存在差异。根据语音可懂度指数(SII)框架定义的带重要性函数(BIF)用于量化跨频率区域的贡献。从 16 名母语为普通话的成年人那里估计了三种语音材料的 BIF。使用贝叶斯自适应程序,为每个听众高效地估计了三种材料的倍频程 BIF。随着语境信息量的增加,低频带(例如 250 和 500Hz)对语音识别变得更加重要,这与英语的情况一致。普通话的 BIF 比可比的英语语音材料更平坦。将语言和材料特定的 BIF 引入 SII 模型,可提高对普通话语音识别性能的预测。结果表明,有必要为普通话开发特定于材料的 BIF。