VOA标准英语2011--Artificial Speech Mimics Real Thing

Artificial Speech Mimics 1 Real Thing

合成声音发展渐入佳境 未来虚拟声音真假难辨

At a University of Arizona laboratory, Professor Brad Story analyzes 2 the voices of singers, actors and public speakers both live and on audio tape.

在亚利桑那大学实验室, Brad·Story教授分析现场及录影带中歌手,演员及公众演讲的声音。



Computers break down speech digitally. Magnetic-resonance equipment freezes images of the throat, tongue, teeth, and lips as they create sound.

电脑将声音数字化分解。磁力共振设备在产生声音的时候将发声者的喉咙、舌头、牙齿、嘴唇的行为停滞。



This is pure research, but it has practical applications. Story’s findings may one day help performers and those suffering from Parkinson’s Disease and other medical conditions. In the former case, it looks like it won’t be long before singers can employ synthesized backup singers.

这是纯粹的理论研究,但它具有实际用途。Story的发现可能有一天会帮助表演者和帕金森病的患者及其他医疗状况。看来不用多久,歌手就可以合成背景人工歌曲。



In the latter case, this research can help the medical community develop therapy that improves patients’ quality of speech.

在后一情况下,本研究可以帮助医疗机构改善病人治疗疗效。



Story is especially fascinated by synthetic 3 voices, used in everything from video games to machines that translate documents into spoken words for the visually impaired 4. He is working to make these artificial voices sound more human by re-creating the complicated physics that go into the production of speech.

Story特别着迷于合成应用于各个方面的声音,从电子游戏到为残障人士而设计的翻译文件成为真人语音的机器。通过把演讲中的语言重新创造成复杂的物理符号，他致力于使这些人造声音能够更人化。



They include the intake 5 of air into one’s lungs, the mechanics of vocal 6 folds in the larynx, and the movement of acoustic 7 waves through the vocal tract 8.

这些包括人体摄入肺中的空气量 ,喉咙中的声音震荡，声道中的声波等等。

Artificial speech will one day be so advanced that it could be difficult to differentiate 9 beween real and made-up sound.

Typical synthesized speech sounds robotic because it’s difficult to duplicate human anatomy 10. Story says that’s because it takes more muscles to say a few words than it does to play the piano.

典型的合成语音听起来像机器人是因为很难复制人体解剖。Story表示是因为说几句话就需要更多的肌肉运动。



Story says singing is in some ways easier to simulate, because it tends to have long, sustained vowels 11, a more precise pitch, and a musical score to mask the imperfections. There is already a singing synthesizer, marketed by the Japanese company Yamaha, called “Vocaloid,” that allows users to compose and perform new songs.

Story表示唱歌在某些方面更容易模拟,因为它往往会有长的、持续的元音，更精准的高音,掩盖瑕疵的配乐。日本雅马哈公司已经有一种被称为“Vocaloid”的唱歌合成器,它允许用户作曲及演奏新的歌曲。



Once scientists are successful in duplicating whole blocks of speech, Story says, surgeons can predict how patients will sound after throat surgery, and can make synthesized speech sound realistic for patients who cannot speak at all.

一旦科学家成功复制大部分的语言, Story表示,外科医生就能够预测患者咽喉手术后的发声状况,合成语音会使不能说话的患者音色听起来很真实。



And some day, he confidently predicts, the general public will hear artificial speech on the telephone, in games, and on buses and subways that sounds so natural, we’ll have a difficult time telling the difference between real and made-up human voices.

有一天,他自信地预测,公众演讲将听到电话、游戏、公共汽车和地铁的自然人工语音,我们将很难分辨真实和虚拟的声音。