Barbara Schuppler

How stable are acoustic metrics of contrastive speech rhythm

Acoustic metrics of contrastive speech rhythm, based on vocalic and intervocalic interval durations, are intended to capture stable typological differences between languages. They should consequently be robust to variation between speakers, sentence materials, and measurers. This paper assesses the impact of these sources of variation on the metrics %V (proportion of utterance comprised of vocalic intervals), VarcoV (rate-normalized standard deviation of vocalic interval duration), and nPVI-V (a measure of the durational variability between successive pairs of vocalic intervals). Five measurers analyzed the same corpus of speech: five sentences read by six speakers of Standard Southern British English. Differences between sentences were responsible for the greatest variation in rhythm scores. Inter-speaker differences were also a source of significant variability. However, there was relatively little variation due to segmentation differences between measurers following an agreed protocol. An automated phone alignment process was also used: Rhythm scores thus derived showed good agreement with the human measurers. A number of recommendations for researchers wishing to exploit contrastive rhythm metrics are offered in conclusion.

Acoustic reduction in conversational Dutch: A quantitative analysis based on automatically generated segmental transcriptions

Abstract In spontaneous, conversational speech, words are often reduced compared to their citation forms, such that a word like yesterday may sound like [ ’ j e ʃ e I ] . The present chapter investigates such acoustic reduction. The study of reduction needs large corpora that are transcribed phonetically. The first part of this chapter describes an automatic transcription procedure used to obtain such a large phonetically transcribed corpus of Dutch spontaneous dialogues, which is subsequently used for the investigation of acoustic reduction. First, the orthographic transcriptions were adapted for automatic processing. Next, the phonetic transcription of the corpus was created by means of a forced alignment using a lexicon with multiple pronunciation variants per word. These variants were generated by applying phonological and reduction rules to the canonical phonetic transcriptions of the words. The second part of this chapter reports the results of a quantitative analysis of reduction in the corpus on the basis of the generated transcriptions and gives an inventory of segmental reductions in standard Dutch. Overall, we found that reduction is more pervasive in spontaneous Dutch than previously documented.

How linguistic and probabilistic properties of a word affect the realization of its final /t/: Studies at the phonemic and sub-phonemic level

Abstract This paper investigates the realization of word-final /t/ in conversational standard Dutch. First, based on a large number of word tokens (6747) annotated with broad phonetic transcription by an automatic transcription tool, we show that morphological properties of the words and their position in the utterances syntactic structure play a role for the presence versus absence of their final /t/. We also replicate earlier findings on the role of predictability (word frequency and bigram frequency with the following word) and provide a detailed analysis of the role of segmental context. Second, we analyze the detailed acoustic properties of word-final /t/ on the basis of a smaller number of tokens (486) which were annotated manually. Our data show that word and bigram frequency as well as segmental context also predict the presence of sub-phonemic properties. The investigations presented in this paper extend research on the realization of /t/ in spontaneous speech and have potential consequences for psycholinguistic models of speech production and perception as well as for automatic speech recognition systems.

Using temporal information for improving articulatory-acoustic feature classification

This paper combines acoustic features with a high temporal and a high frequency resolution to reliably classify articulatory events of short duration, such as bursts in plosives. SVM classification experiments on TIMIT and SVArticulatory showed that articulatory-acoustic features (AFs) based on a combination of MFCCs derived from a long window of 25ms and a short window of 5ms that are both shifted with 2.5ms steps (Both) outperform standard MFCCs derived with a window of 25 ms and a shift of 10 ms (Baseline). Finally, comparison of the TIMIT and SVArticulatory results showed that for classifiers trained on data that allows for asynchronously changing AFs (SVArticulatory) the improvement from Baseline to Both is larger than for classifiers trained on data where AFs change simultaneously with the phone boundaries (TIMIT).

Automatic Phonetic Transcription in Two Steps: Forced Alignment and Burst Detection

In the last decade, there was a growing interest in conversational speech in the fields of human and automatic speech recognition. Whereas for the varieties spoken in Germany, both resources and tools are numerous, for Austrian German only recently the first corpus of read and conversational speech was collected. In the current paper, we present automatic methods to phonetically transcribe and segment (read and) conversational Austrian German. For this purpose, we developed an automatic two-step transcription procedure: In the first step, broad phonetic transcriptions are created by means of a forced alignment and a lexicon with multiple pronunciation variants per word. In the second step, plosives are annotated on the sub-phonemic level: an automatic burst detector automatically determines whether a burst exists and where it is located. Our preliminary results show that the forced alignment based approach reaches accuracies in the range of what has been reported for the inter-transcriber agreement for conversational speech. Furthermore, our burst detector outperforms previous tools with accuracies between 98 % and 74 % for the different conditions in read speech, and between 82 % and 52 % for conversational speech.