Artificial personality and disfluency

نویسندگان

  • Mirjam Wester
  • Matthew P. Aylett
  • Marcus Tomalin
  • Rasmus Dall
چکیده

The focus of this paper is artificial voices with different personalities. Previous studies have shown links between an individual’s use of disfluencies in their speech and their perceived personality. Here, filled pauses (uh and um) and discourse markers (like, you know, I mean) have been included in synthetic speech as a way of creating an artificial voice with different personalities. We discuss the automatic insertion of filled pauses and discourse markers (i.e., fillers) into otherwise fluent texts. The automatic system is compared to a ground truth of human “acted” filler insertion. Perceived personality (as defined by the big five personality dimensions) of the synthetic speech is assessed by means of a standardised questionnaire. Synthesis without fillers is compared to synthesis with either spontaneous or synthetic fillers. Our findings explore how the inclusion of disfluencies influences the way in which subjects rate the perceived personality of an artificial voice.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A comparison between a DNN and a CRF disfluency detection and reconstruction system

We propose to compare between a Deep Neural Network and a Conditional Random Field disfluency detection and reconstruction system, both trained on the same features. Deep Neural Networks, despite an increasing popularity in a multitude of speech and language related tasks, were never applied to disfluency recognition. One of the most difficult classes of disfluency is false starts. We are inter...

متن کامل

Disfluency Detection Using a Bidirectional LSTM

We introduce a new approach for disfluency detection using a Bidirectional Long-Short Term Memory neural network (BLSTM). In addition to the word sequence, the model takes as input pattern match features that were developed to reduce sensitivity to vocabulary size in training, which lead to improved performance over the word sequence alone. The BLSTM takes advantage of explicit repair states in...

متن کامل

Phonetic evidence for two types of disfluency

Disfluency, such as pause (silences), filled pause (e.g., ‘um’, ‘uh’), repetition (e.g., ‘the the’) and cutoff word (e.g., ‘hori[zontal]-’), is a common part of human speech that occurs at a rate of 6 to 10 per 100 words [2, 5]. According to one model of speech production [8], there are two types of disfluency: disfluency at the internal planning stage (e.g., wordretrieval difficulties), and di...

متن کامل

Characteristics of disfluency clusters in adults who stutter.

BACKGROUND/AIMS The purpose of this study was to examine characteristics of disfluency clusters in adults who stutter (AWS) and to compare these characteristics to those previously reported for children who stutter (CWS). METHOD The spontaneous speech of ten AWS was sampled and organized according to utterance length in syllables. The overall number and type of disfluency clusters occurring i...

متن کامل

The Effects of Disfluency Detection in Parsing Spoken Language

Spoken language contains disfluencies that, because of their irregular nature, may lead to reduced performance of data-driven parsers. This paper describes an experiment that quantifies the effects of disfluency detection and disfluency removal on data-driven parsing of spoken language data. The experiment consists of creating two reduced versions from a spoken language treebank, the Switchboar...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2015