In conventional speech synthesis, large amounts of phonetically balanced speech data recorded in highly controlled recording studio environments are typically required to build a voice. Although using such data is a straightforward solution for high quality synthesis, the number of voices available will always be limited, because recording costs are high. On the other hand, our recent experiments with HMM-based speech synthesis systems have demonstrated that speaker-adaptive HMM-based speech synthesis (which uses an "average voice model" plus model adaptation) is robust to non-ideal speech data that are recorded under various conditions and with varying microphones, that are not perfectly clean, and/or that lack phonetic balance. This enables us to consider building high-quality voices on "non-TTS" corpora such as ASR corpora. Since ASR corpora generally include a large number of speakers, this leads to the possibility of producing an enormous number of voices automatically. In this paper, we demonstrate the thousands of voices for HMM-based speech synthesis that we have made from several popular ASR corpora such as the Wall Street Journal (WSJ0, WSJ1, and WSJCAM0), Resource Management, Globalphone, and SPEECON databases.

This paper describes a speaker discrimination experiment in which native English listeners were presented with natural and synthetic speech stimuli in English and were asked to judge whether they thought the sentences were spoken by the same person or not. The natural speech consisted of recordings of Finnish speakers speaking English. The synthetic stimuli were created using adaptation data from the same Finnish speakers. Two average voice models were compared: one trained on Finnish-accented English and the other on American-accented English. The experiments illustrate that listeners perform well at speaker discrimination when the stimuli are both natural or both synthetic, but when the speech types are crossed performance drops significantly. We also found that the type of accent in the average voice model had no effect on the listeners' speaker discrimination performance.

No abstract

For researching effects of gamification in foreign language learning for children in the "Say It Again, Kid!" project we developed a feedback paradigm that can drive gameplay in pronunciation learning games. We describe our scoring system based on the difference between a reference phone sequence and the output of a multilingual CTC phoneme recogniser. We present a white-box scoring model of mapped weighted Levenshtein edit distance between reference and error with error weights for articulatory differences computed from a training set of scored utterances. The system can produce a humanreadable list of each detected mispronunciation's contribution to the utterance score. We compare our scoring method to established black box methods.

Kuronen, M., P. Lintunen & T. Nieminen (toim.) . Näkökulmia This study inves gates whether temporal features in speech can predict the perceived proficiency level in Finnish learners of Swedish. In so doing, seven expert raters assessed speech samples produced by upper secondary school students using the revised CEFR scale for phonological control. The effect of temporal features was studied with a cumula ve link mixed model, and the assessments were further analyzed to study inter-rater varia on. The results indicate that ar cula on rate and certain types of disfluencies in speech can predict the perceived proficiency level. Furthermore, assessors seem to weigh temporal features differently depending on the speech type and their individual focus.