| 1. |
- Al Moubayed, Samer, et al.
(författare)
-
Automatic Prominence Classification in Swedish
- 2010
-
Ingår i: Proceedings of Speech Prosody 2010, Workshop on Prosodic Prominence. - Chicago, USA.
-
Konferensbidrag (refereegranskat)abstract
- This study aims at automatically classifying levels of acoustic prominence on a dataset of 200 Swedish sentences of read speech by one male native speaker. Each word in the sentences was categorized by four speech experts into one of three groups depending on the level of prominence perceived. Six acoustic features at a syllable level and seven features at a word level were used. Two machine learning algorithms, namely Support Vector Machines (SVM) and memory based Learning (MBL) were trained to classify the sentences into their respective classes. The MBL gave an average word level accuracy of 69.08% and the SVM gave an average accuracy of 65.17 % on the test set. These values were comparable with the average accuracy of the human annotators with respect to the average annotations. In this study, word duration was found to be the most important feature required for classifying prominence in Swedish read speech
|
|
| 2. |
- Beskow, Jonas, et al.
(författare)
-
Human Recognition of Swedish Dialects
- 2008
-
Ingår i: Proceedings of Fonetik 2008. - Göteborg : Göteborgs universitet. - 9789197719605 ; , s. 61-64
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- Our recent work within the research projectSIMULEKT (Simulating Intonational Varieties of Swedish) involves a pilot perceptiontest, used for detecting tendencies in humanclustering of Swedish dialects. 30 Swedishlisteners were asked to identify the geographical origin of 72 Swedish native speakers by clicking on a map of Sweden. Resultsindicate for example that listeners from thesouth of Sweden are generally better at recognizing some major Swedish dialects thanlisteners from the central part of Sweden.
|
|
| 3. |
|
|
| 4. |
- Beskow, Jonas, et al.
(författare)
-
Recognizing and Modelling Regional Varieties of Swedish
- 2008
-
Ingår i: INTERSPEECH 2008. - 9781615673780 ; , s. 512-515
-
Konferensbidrag (refereegranskat)abstract
- Our recent work within the research project SIMULEKT (Simulating Intonational Varieties of Swedish) includes two approaches. The first involves a pilot perception test, used for detecting tendencies in human clustering of Swedish dialects. 30 Swedish listeners were asked to identify the geographical origin of Swedish native speakers by clicking on a map of Sweden. Results indicate for example that listeners from the south of Sweden are better at recognizing some major Swedish dialects than listeners from the central part of Sweden, which includes the capital area. The second approach concerns a method for modelling intonation using the newly developed SWING (Swedish INtonation Generator) tool, where annotated speech samples are resynthesized with rule based intonation and audiovisually analysed with regards to the major intonational varieties of Swedish. We consider both approaches important in our aim to test and further develop the Swedish prosody model.
|
|
| 5. |
|
|
| 6. |
- Bruce, Gösta, et al.
(författare)
-
Modelling intonation in varieties of swedish
- 2008
-
Ingår i: Proceedings of the 4th International Conference on Speech Prosody, SP 2008. - : International Speech Communications Association. - 9780616220030 ; , s. 571-574
-
Konferensbidrag (refereegranskat)abstract
- The research project Simulating intonational varieties of Swedish (SIMULEKT) aims to gain more precise and thorough knowledge about some major regional varieties of Swedish: South, Göta, Svea, Gotland, Dala, North, and Finland Swedish. In this research effort, the Swedish prosody model and different forms of speech synthesis play a prominent role. The two speech databases SweDia 2000 and SpeechDat constitute our main material for analysis. As a first test case for our prosody model, we compared Svea and North Swedish intonation in a pilot production-oriented perception test. Näi{dotless}ve Swedish listeners were asked to identify the most Svea and North sounding stimuli. Results showed that listeners can differentiate between the two varieties from intonation only. They also provided information on how intonational parameters affect listeners' impression of Swedish varieties. All this indicates that our experimental method can be used to test perception of different regional varieties of Swedish.
|
|
| 7. |
- Enflo, Laura, 1980-
(författare)
-
Alternative Measures of Phonation: Collision Threshold Pressure and Electroglottographic Spectral Tilt : Extra: Perception of Swedish Accents
- 2010
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The collision threshold pressure (CTP), i.e. the smallest amount of subglottal pressure needed for vocal fold collision, has been explored as a possible complement or alternative to the now commonly used phonation threshold pressure (PTP), i.e. the smallest amount of subglottal pressure needed to initiate and sustain vocal fold oscillation. In addition, the effects of vocal warm-up (Paper 1) and vocal loading (Paper 2) on the CTP and the PTP have been investigated. Results confirm previous findings that PTP increases with an increase in fundamental frequency (F0) of phonation and this is true also for CTP, which on average is about 4 cm H2O higher than the PTP. Statistically significant increases of the CTP and PTP after vocal loading were confirmed and after the vocal warm-up, the threshold pressures were generally lowered although these results were significant only for the females. The vocal loading effect was minor for the two singer subjects who participated in the experiment of Paper 2. In Paper 3, the now commonly used audio spectral tilt (AST) is measured on the vowels of a large database (5277 sentences) containing speech of one male Swedish actor. Moreover, the new measure electroglottographic spectral tilt (EST) is calculated from the derivatives of the electroglottographic signals (DEGG) of the same database. Both AST and EST were checked for vowel dependency and the results show that while AST is vowel dependent, EST is not. Paper 4 reports the findings from a perception experiment on Swedish accents performed on 47 Swedish native speakers from the three main parts of Sweden. Speech consisting of one sentence chosen for its prosodically interesting properties and spoken by 72 speakers was played in headphones. The subjects would then try to locate the origin of every speaker on a map of Sweden. Results showed for example that the accents of the capital of Sweden (Stockholm), Gotland and southern Sweden were the ones placed correctly to the highest degree.
|
|
| 8. |
- Enflo, Laura, et al.
(författare)
-
Collision and Phonation Threshold Pressures Before and After Loud, Prolonged Vocalization in Trained and Untrained Voices
- 2013
-
Ingår i: Journal of Voice. - : Elsevier BV. - 0892-1997 .- 1873-4588. ; 27:5, s. 527-530
-
Tidskriftsartikel (refereegranskat)abstract
- The phonation threshold pressure (PTP) is defined as the lowest subglottal pressure needed for obtaining and sustaining vocal fold oscillation. It has been found to increase during vocal fatigue. In the present study, PTP is measured together with the threshold pressure needed for vocal fold collision; henceforth, the collision threshold pressure (CTP). PTP and CTP are compared before and after loud, prolonged vocalization in singer and nonsinger voices. Ten subjects repeated the vowel sequence /a, e, i, o, u/ at a Sound Pressure Level of at least 80 dB at 0.3 m for 20 minutes. Audio and electroglottography signals were recorded before and after this exercise. At the same time, oral pressure was registered while the subjects produced a diminuendo repeating the syllable /pa:/, thus acquiring an approximate of the subglottal pressure. CTP and PTP increased significantly after the vocal loading in the nonsinger subjects. On the other hand, singers reported no substantial effect of the exercise, and most singers had a mean after-to-before ratio close to 1 for both CTP and PTP.
|
|
| 9. |
- Enflo, Laura
(författare)
-
Collision Threshold Pressure : A novel measure of voice function Effects of vocal warm-up, vocal loading and resonance tube phonation in water
- 2013
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The phonation threshold pressure (PTP), i.e., the smallest amount of subglottal pressure needed to initiate and sustain vocal fold oscillation, is frequently difficult to measure due to the difficulty for some subjects to produce extremely soft phonation. In addition, PTP values are often quite scattered. Hence, the collision threshold pressure (CTP), i.e., the smallest amount of subglottal pressure needed for vocal fold collision, was explored as a possible complement or alternative to PTP. Effects on CTP and PTP of vocal warm-up (Paper 1), resonance tube phonation with the tube end in water (Paper 2), and vocal loading (Paper 3) were investigated. With the aim to accelerate the CTP measurement process, comparisons were made between CTP values derived manually and those derived by several automatic or semi-automatic parameters (Paper 4).Subjects were recorded at various F0 while phonating /pa:/-sequences, starting at medium loudness and continuing until phonation ceased. Subglottal pressure was estimated from oral pressure signals during the /p/ occlusion. Vocal fold contact was determined manually from the amplitude of the electroglottographic (EGG) signal (Papers 1 and 3) or its first derivative (dEGG) (Papers 2 and 4).Recordings were made before and after exercise: (Paper 1) Vocal warm-up was carried out in the 13 singers’ own habitual way. (Paper 2) Twelve mezzo-sopranos phonated on /u:/ at various pitches for two minutes before post-recording, and 15 seconds before each additional F0, into a glass tube (l=27 cm, id=9 mm) at a water depth of 1-2 cm.(Paper 3) Five trained singers and five untrained subjects repeated the vowel sequence /a,e,i,o,u/ at a Sound Pressure Level of at least 80 dB at 0.3 m for 20 minutes.Statistically significant results: (Paper 1) CTP and PTP decreased after warm-up in the five female voices. CTP was found to be higher than PTP (about 4 H2O). Also, CTP had a lower coefficient of variation, suggesting that CTP is a more reliable measure than PTP. (Paper 2) CTP increased on average six percent after resonance tube phonation in water.(Paper 3) CTP and PTP increased after the vocal loading in the untrained voices, with an average after-to-before ratio of 1.26 for CTP and 1.33 for PTP.(Paper 4) Automatically derived CTP values showed high correlation with those obtained manually, from EGG spectrum slope, and from the visual displays of dEGG and of dEGG wavegram.
|
|
| 10. |
- Enflo, Laura, 1980-, et al.
(författare)
-
Collision Threshold Pressure Before and After Vocal Loading
- 2009
-
Ingår i: INTERSPEECH 2009. - 9781615676927 ; , s. 764-767
-
Konferensbidrag (refereegranskat)abstract
- The phonation threshold pressure (PIP) has been found to increase during vocal fatigue. In the present study we compare PTP and collision threshold pressure (CTP) before and after vocal loading in singer and non-singer voices. Seven subjects repeated the vowel sequence /a,c,i,o,u/ at an SPL of at least 80 dB @ 0.3 m for 20 min. Before and after this loading the subjects' voices were recorded while they produced a diminuendo repeating the syllable /pa/. Oral pressure during the /p/ occlusion was used as a measure of subglottal pressure. Both CTP and PIP increased significantly after the vocal loading.
|
|
