Få maskiner att tala: Formulera forskningsfrågor

The Challenge

Speech synthesis—in which a machine generates human-like speech—has applications in basic linguistic research, assistive technologies for people with disabilities, and commercial devices and software. Of particular interest are text-to-speech (TTS) systems. Mute people who rely on speech synthesis to express themselves verbally are best served by synthesizers capable of producing a range of women and men’s voices: Synthesizing sex and gender in speech is important to how speech is perceived and interpreted (Nass et al., 2005).

Key Method: Analyzing Gender

Gender assumptions can influence both the act of speaking and the act of listening (or interpreting what is heard) even when the speaker is a machine. Voices encode rich information about the speaker—such as sex, gender, age, and often nationality—even if such information is never directly articulated. Analyzing sex (biological factors) and gender (socio-cultural factors) is important for creating TTS systems with a range of voices for assistive technologies and other human/computer interface.

Gendered Innovations:

  1. Text-To-Speech Technologies Producing both Women and Men’s Voices: Text-to-speech system engineers who rethought research priorities and outcomes and recognized the importance of producing both women and men’s voices created new products, such as DECTalk (1984). Flexible speech synthesizers capable of producing voices representing women and men of different ages, gender identities, and regional dialects help fit voice characteristics to users.
  2. Understanding Gender in Speech: By Analyzing Gender researchers better understand how social identities are communicated in speech. Computerized TTS systems are effectively social actors, and the messages they send depend upon the underlying technology, uses, and users' responses.